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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 43872
    Prev
    Next
    INDEX
    Explanations

    terms indicating specific references or focuses within a text

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

    introduces specific situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.37
    k
    -0.31
     and
    -0.29
    ly
    -0.29
     I
    -0.29
    -
    -0.28
    .
    -0.28
    4
    -0.27
     &
    -0.27
    1
    -0.27
    POSITIVE LOGITS
     يتيمه
    1.14
    expandindo
    1.03
    ſſung
    0.97
    <unused79>
    0.97
    niſſe
    0.97
    <unused52>
    0.96
     للمعارف
    0.96
    <unused41>
    0.96
    <unused3>
    0.96
    <unused14>
    0.96
    Activations Density 0.073%

    No Known Activations