© 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. 9-GEMMASCOPE-RES-131K
    6. 17454
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly periods and semicolons, usually indicating the end of statements in code or sentences

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

    code structure punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.86
    adaptiveStyles
    -0.86
    MessageOf
    -0.79
    
    -0.77
    AISSEE
    -0.77
    WithIOException
    -0.75
     <<<<<<<<<<<<<<
    -0.75
    awtextra
    -0.75
    GraphicsUnit
    -0.74
     kaarangay
    -0.73
    POSITIVE LOGITS
    ;
    0.29
    .
    0.29
    /
    0.29
    葬
    0.28
     zwar
    0.28
    Бахар
    0.28
    routing
    0.28
     nahilalakip
    0.28
     /
    0.28
     StatelessWidget
    0.27
    Activations Density 0.002%

    No Known Activations