Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5113
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and emotional states

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

    "I am" or "it is"

    np_acts-logits-general · gemini-2.0-flash

    I am in a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.76
     صوتيه
    -0.74
    multicolumn
    -0.64
     transfieras
    -0.64
     gonna
    -0.64
     /\.
    -0.61
     wanna
    -0.61
    сихо
    -0.60
    InputBorder
    -0.60
    PyErr
    -0.60
    POSITIVE LOGITS
    mektedir
    0.79
    lisi
    0.73
    \,.
    0.72
    aarrggbb
    0.69
    melidir
    0.69
     للاسماء
    0.68
     nomme
    0.67
    upported
    0.66
    cination
    0.65
    États
    0.65
    Activations Density 0.388%

    No Known Activations