© 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. 43975
    Prev
    Next
    INDEX
    Explanations

    conditional or causal statements related to kidney health

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

    conjunctions and connecting phrases

    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
     ujednoznacz
    -0.38
     namorados
    -0.33
    TagMode
    -0.33
     informée
    -0.32
     declaraciones
    -0.31
    estacks
    -0.31
     punggung
    -0.30
    ⓘ
    -0.30
     lucru
    -0.29
    kozások
    -0.28
    POSITIVE LOGITS
     Usually
    0.60
     Actually
    0.60
     it
    0.59
     Specially
    0.57
    Actually
    0.57
     autorytatywna
    0.57
    matchCondition
    0.56
    kmale
    0.56
     Need
    0.56
     Beside
    0.56
    Activations Density 0.046%

    No Known Activations