© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38493
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure, particularly related to function definitions and parameters

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

    client arguments and fields

    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
     EconPapers
    -0.57
     saites
    -0.50
    httphttps
    -0.46
     henvisninger
    -0.44
    RenderAtEndOf
    -0.43
    EnumMember
    -0.43
     chi̍t
    -0.42
     <<<<<<<<<<<<<<
    -0.42
     hab
    -0.40
    Jegyzetek
    -0.40
    POSITIVE LOGITS
    什么呢
    0.50
     orderBy
    0.44
     >=",
    0.44
     dieselben
    0.43
    條件
    0.42
     propOrder
    0.42
     through
    0.42
     gennem
    0.42
     Reihenfolge
    0.42
    StackNavigator
    0.41
    Activations Density 0.003%

    No Known Activations