© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105707
    Prev
    Next
    INDEX
    Explanations

    terminology related to layering and binding processes in materials or biological systems

    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
     betweenstory
    -0.54
    complished
    -0.51
     PrintWriter
    -0.49
    DispatchToProps
    -0.47
    \{\\
    -0.47
     dieß
    -0.46
    alyptus
    -0.46
    tonode
    -0.46
    DataAnnotations
    -0.45
    dresser
    -0.44
    POSITIVE LOGITS
    awtextra
    0.45
    complexContent
    0.44
    expandindo
    0.43
    ThroughAttribute
    0.39
     addSubview
    0.38
     incorporación
    0.37
     BorderLayout
    0.37
     дописавши
    0.36
     Winaray
    0.36
    oa̍t
    0.36
    Activations Density 0.300%

    No Known Activations