© 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. 21685
    Prev
    Next
    INDEX
    Explanations

    references to software generation and licensing

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

    generated by

    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
    InitStruct
    -0.44
    AntiForgeryToken
    -0.44
     tenisky
    -0.44
    UnknownFieldSet
    -0.43
     Maggiore
    -0.42
     getItemId
    -0.42
    PreferredItem
    -0.42
    UnknownFields
    -0.42
     scoops
    -0.41
    balleur
    -0.41
    POSITIVE LOGITS
    发表于
    0.58
    }}]{
    0.51
     tool
    0.50
     Audiodateien
    0.50
    工具
    0.48
     tools
    0.46
     Wings
    0.46
    tools
    0.45
     resourceCulture
    0.43
     незавершена
    0.43
    Activations Density 0.001%

    No Known Activations