© 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. 20-GEMMASCOPE-RES-131K
    11. 28625
    Prev
    Next
    INDEX
    Explanations

    code-related terms and references to programming or web development components

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

    HTML attributes and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.31
    .
    -0.30
    assertEqual
    -0.27
     getItemCount
    -0.26
     Cou
    -0.26
    目
    -0.25
    L
    -0.25
    作
    -0.25
     miss
    -0.25
     sa
    -0.25
    POSITIVE LOGITS
     nahilalakip
    0.84
    httphttps
    0.81
    الحياه
    0.78
     يتيمه
    0.73
    Diwedd
    0.72
    IVEREF
    0.70
    ConstraintMaker
    0.70
    iſten
    0.69
    iſen
    0.69
     defaultstate
    0.69
    Activations Density 0.001%

    No Known Activations