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. 38130
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials or additional information related to academic papers

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

    Nature publisher DOIs

    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
     pétrole
    -0.39
     víctima
    -0.36
     Oregon
    -0.35
     vœ
    -0.35
     héroe
    -0.34
    Oregon
    -0.33
     computadoras
    -0.33
     aient
    -0.32
     víctimas
    -0.31
     certificados
    -0.30
    POSITIVE LOGITS
     Nature
    0.71
    nature
    0.69
    providedIn
    0.68
    Nature
    0.67
    NATURE
    0.66
     NATURE
    0.64
    autorest
    0.64
     ***!
    0.64
     nature
    0.63
    APORE
    0.58
    Activations Density 0.086%

    No Known Activations