© 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. 30102
    Prev
    Next
    INDEX
    Explanations

    references to blog activity and management

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

    communication updates

    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
    ScopeManager
    -0.40
    دانشنامهٔ
    -0.38
     verantwoorde
    -0.35
    onomian
    -0.35
    ьажоргаш
    -0.34
    lotl
    -0.34
    specialchars
    -0.33
    RuleContext
    -0.33
    Specifier
    -0.33
    ModelBuilder
    -0.33
    POSITIVE LOGITS
    twimg
    0.65
    المشاركات
    0.53
     emails
    0.48
    scriptcase
    0.48
     ligiloj
    0.47
     newsletters
    0.46
    setCellStyle
    0.45
    críbete
    0.45
     posts
    0.45
     newsletter
    0.45
    Activations Density 0.031%

    No Known Activations