© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15919
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection and realizations regarding one's purpose in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    I, years, life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.65
    TemporalType
    -0.58
    +#+#
    -0.54
    彼らは
    -0.54
    onAttach
    -0.52
     SwitchCompat
    -0.52
    UnusedPrivate
    -0.51
    Gweler
    -0.51
    ⓧ
    -0.51
     Réponses
    -0.51
    POSITIVE LOGITS
    Being
    0.76
     Being
    0.76
     years
    0.73
     ever
    0.72
    Growing
    0.70
     being
    0.70
     life
    0.69
    being
    0.68
    Years
    0.67
     årene
    0.66
    Activations Density 0.296%

    No Known Activations