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. 10-GEMMASCOPE-RES-16K
    6. 4557
    Prev
    Next
    INDEX
    Explanations

    interactions involving guessing or determining the correctness of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toolStripButton
    -0.60
     NavController
    -0.54
    actéristique
    -0.51
    nictwa
    -0.50
     bè
    -0.49
    imation
    -0.49
    }';
    -0.48
    bourhood
    -0.47
     lệ
    -0.46
    uchung
    -0.46
    POSITIVE LOGITS
     guessed
    1.00
     guesses
    0.94
     guess
    0.93
     guessing
    0.89
     Guess
    0.83
    guess
    0.77
    Guess
    0.72
    猜
    0.72
     gues
    0.70
     correctly
    0.66
    Activations Density 0.360%

    No Known Activations