© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements used in programming

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

    is checks for true/false states

    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
    bootstrapcdn
    -0.37
    umn
    -0.34
    Cav
    -0.34
     StatefulWidget
    -0.33
    avannah
    -0.33
    以下の
    -0.33
    athyroid
    -0.33
     Fonten
    -0.33
    elemento
    -0.32
     deltag
    -0.32
    POSITIVE LOGITS
     betweenstory
    1.09
     isComment
    0.76
     setIs
    0.72
     getIs
    0.63
    getIs
    0.63
     Is
    0.60
    Kaynakça
    0.59
     indígen
    0.59
     IS
    0.58
    Is
    0.57
    Activations Density 0.037%

    No Known Activations