© 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. 44119
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial concepts, including contracts and intellectual property

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

    specific nouns

    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
     الرياضيه
    -0.84
     وتسجيلات
    -0.78
     ligiloj
    -0.75
     poveznice
    -0.75
     Verſ
    -0.72
     CanadaChoose
    -0.72
    yntaxException
    -0.68
     defaultstate
    -0.68
    DeleteBehavior
    -0.68
     $_(
    -0.67
    POSITIVE LOGITS
     toute
    0.38
     
    0.38
    ↵↵
    0.37
    W
    0.37
    Stan
    0.36
    Do
    0.35
     free
    0.34
    -
    0.34
    All
    0.34
    ded
    0.34
    Activations Density 0.555%

    No Known Activations