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. 12286
    Prev
    Next
    INDEX
    Explanations

    sections of code that indicate organizational or structural components in programming, particularly related to user interface elements

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

    programming code and syntax

    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
    OGND
    -0.69
     كومونز
    -0.53
     للاسماء
    -0.52
    (!__
    -0.50
    ロウィン
    -0.49
    AndroidJUnit
    -0.49
    Архівовано
    -0.49
    Története
    -0.47
     censiti
    -0.47
    ConstraintMaker
    -0.46
    POSITIVE LOGITS
    "));
    
    0.48
     Private
    0.47
    "]);
    
    0.46
    WebElementEntity
    0.44
     private
    0.43
    "]
    
    0.42
     Public
    0.41
    '));
    
    0.41
    ']);
    
    0.41
    <>();
    
    0.41
    Activations Density 0.003%

    No Known Activations