© 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. 746
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure related to React components

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

    code-related keywords and components in a React framework context

    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
    ArrowToggle
    -0.45
    itesi
    -0.45
     Civil
    -0.44
     Πολ
    -0.43
     PyTuple
    -0.40
    createNewFile
    -0.40
    ftime
    -0.40
    httpResponse
    -0.38
    ucker
    -0.38
    ृ
    -0.38
    POSITIVE LOGITS
    
    0.80
     ExecuteAsync
    0.74
     насељу
    0.72
     незавершена
    0.71
     становника
    0.70
    ActionCreators
    0.70
     Autorisations
    0.67
     ویکی‌پدیا
    0.66
    mapStateToProps
    0.66
    Παραπομπές
    0.63
    Activations Density 0.008%

    No Known Activations