© 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. 121938
    Prev
    Next
    INDEX
    Explanations

    evidence of personal actions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    genodigd
    -0.40
     Exacts
    -0.39
    TargetException
    -0.38
    ፩
    -0.36
    :+:
    -0.35
     Mahmud
    -0.35
    ılmıştır
    -0.35
    Xna
    -0.35
    ically
    -0.34
     zvíř
    -0.34
    POSITIVE LOGITS
    Tembelea
    0.57
    
    0.50
    
    0.45
    QMetaType
    0.45
    scriptId
    0.44
     EconPapers
    0.44
    writeField
    0.44
    ViewFeatures
    0.43
    RenderAtEndOf
    0.42
    ſelf
    0.41
    Activations Density 0.046%

    No Known Activations