© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102919
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to functions and method definitions

    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
    EDEFAULT
    -1.00
     ब्रेकडाउन
    -0.77
    CodeAttribute
    -0.68
    ⟬
    -0.64
    writeFieldEnd
    -0.63
     AssemblyCulture
    -0.60
    xase
    -0.59
     Biôgrafia
    -0.58
     <>",
    -0.58
    OCCURRED
    -0.57
    POSITIVE LOGITS
    Eloquent
    0.56
    hasMany
    0.42
    belongsTo
    0.41
    WithMany
    0.40
     en
    0.37
     Her
    0.36
    ManyToOne
    0.36
     She
    0.35
     relations
    0.34
     zur
    0.34
    Activations Density 0.004%

    No Known Activations