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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104848
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    :✨
    -0.61
    dafx
    -0.57
    Попис
    -0.55
     المعيارى
    -0.50
    Personendaten
    -0.50
     Walkover
    -0.48
    oa̍t
    -0.47
    хьтан
    -0.46
    QMetaType
    -0.46
     typelib
    -0.44
    POSITIVE LOGITS
    GOTREF
    0.53
    WriteLiteral
    0.50
     getRule
    0.44
     дописавши
    0.41
    PerformLayout
    0.41
    </thead>
    0.38
    parsedMessage
    0.38
    live
    0.38
     Anyway
    0.37
     Enough
    0.37
    Activations Density 0.036%

    No Known Activations