© 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. 21625
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts

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

    decode repeated singular message field

    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
    ագրություններ
    -0.35
     “
    -0.34
     "
    -0.33
     ‘
    -0.32
     normal
    -0.32
     $
    -0.31
     
    -0.30
     non
    -0.29
     maximum
    -0.29
     extra
    -0.28
    POSITIVE LOGITS
    ThroughAttribute
    0.82
    DebuggerNonUser
    0.75
     kasarigan
    0.69
    bootstrapcdn
    0.69
     defaultstate
    0.68
     Geſch
    0.67
    RenderAtEndOf
    0.65
    HtmlAttribute
    0.64
    ifflin
    0.62
    исленность
    0.61
    Activations Density 0.001%

    No Known Activations