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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4772
    Prev
    Next
    INDEX
    Explanations

    numeric and tabular data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.39
    .
    -0.35
    ↵↵
    -0.34
    1
    -0.33
     home
    -0.32
     concevoir
    -0.31
    ?
    -0.31
    …
    -0.31
     fonctionner
    -0.31
     himself
    -0.31
    POSITIVE LOGITS
    aarrggbb
    0.84
    OGND
    0.82
    évaluateur
    0.81
    SharedDtor
    0.71
     للاسماء
    0.71
    出版年
    0.69
    outSlope
    0.69
    featureID
    0.68
    ArrowToggle
    0.67
    posedge
    0.67
    Activations Density 2.599%

    No Known Activations