© 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. 38513
    Prev
    Next
    INDEX
    Explanations

    references to media recommendations and related content

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

    related items and lists

    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
    centralwidget
    -0.45
    المكان
    -0.44
    arraycopy
    -0.44
    enumii
    -0.42
    Rujuakan
    -0.42
     mergeFrom
    -0.40
    andExpect
    -0.40
    EndContext
    -0.39
     يتيمه
    -0.39
    Wrk
    -0.38
    POSITIVE LOGITS
     Related
    1.13
     related
    1.13
    Related
    1.06
     RELATED
    1.00
    RELATED
    0.99
    related
    0.97
    相关
    0.75
     relacionado
    0.72
    相關
    0.69
    関連
    0.69
    Activations Density 0.017%

    No Known Activations