© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12101
    Prev
    Next
    INDEX
    Explanations

    instances of statements or explanations with a focus on issues or problems

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

    positive feedback and solutions

    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
    principalColumn
    -0.73
    GOTREF
    -0.65
    ագրություններ
    -0.56
     AssemblyCulture
    -0.56
     VizieR
    -0.55
    protoimpl
    -0.54
     createSprite
    -0.54
    
    -0.54
    PreferredItem
    -0.52
     HFILL
    -0.52
    POSITIVE LOGITS
    This
    0.90
    Nice
    0.87
    Interesting
    0.78
     this
    0.77
    Excellent
    0.75
     This
    0.75
    Wonderful
    0.73
    Wow
    0.71
     nice
    0.71
     excellent
    0.70
    Activations Density 0.044%

    No Known Activations