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. 20-GEMMASCOPE-RES-131K
    6. 38232
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to software configuration

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

    code comments syntax

    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
    findpost
    -0.96
     للاسماء
    -0.86
    fjspx
    -0.76
     betweenstory
    -0.75
     ویکی‌پدی
    -0.74
    parsedMessage
    -0.74
     '\\;'
    -0.73
    ScopeManager
    -0.72
     mxArray
    -0.70
     esternos
    -0.69
    POSITIVE LOGITS
     سرد
    0.35
     benefit
    0.33
    read
    0.33
     if
    0.31
     adjust
    0.31
    you
    0.30
     either
    0.30
    go
    0.30
    letter
    0.30
     use
    0.29
    Activations Density 0.029%

    No Known Activations