© 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. 738
    Prev
    Next
    INDEX
    Explanations

    elements related to programming logic and structure

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

    programming constructs or keywords related to object manipulation and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    sidemargin
    -0.61
     subject
    -0.57
     Subject
    -0.50
     getResources
    -0.50
     resources
    -0.48
     supported
    -0.48
     Anja
    -0.48
     depth
    -0.47
    borderBottom
    -0.46
    subject
    -0.46
    POSITIVE LOGITS
    featureID
    0.66
    المكان
    0.65
    GenerationType
    0.63
     GenerationType
    0.61
    EndInit
    0.60
     @"/
    0.59
    URLException
    0.59
     HasFactory
    0.59
    ibição
    0.59
     للاسماء
    0.58
    Activations Density 0.003%

    No Known Activations