© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 683
    Prev
    Next
    INDEX
    Explanations

    formatted data entries and code structure

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

    code or structured data elements

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

    numerical data and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     للاسماء
    -0.94
    
    -0.85
    Personensuche
    -0.81
    ThroughAttribute
    -0.80
    SequentialGroup
    -0.80
    sizeCache
    -0.79
     ويكيميديا
    -0.78
    Geplaatst
    -0.78
    InjectAttribute
    -0.77
    RegressionTest
    -0.77
    POSITIVE LOGITS
    RenderAtEndOf
    0.43
    \}\\
    0.38
     endforeach
    0.38
    BASEPATH
    0.37
     undang
    0.36
    quelize
    0.36
    []
    0.35
    存于互联网档案馆
    0.35
     GAM
    0.35
    fontName
    0.35
    Activations Density 0.217%

    No Known Activations