© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    references to wheels or circular themes

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

    the word "wheely" or related terms about wheels

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

    words starting with whe

    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
    saraba
    -0.75
    DataAnnotations
    -0.72
    商品説明
    -0.71
    routeProvider
    -0.71
    quelize
    -0.68
    tangentMode
    -0.68
    
    -0.67
    ينه
    -0.67
    Geplaatst
    -0.66
    kuuta
    -0.63
    POSITIVE LOGITS
     Whe
    0.84
    Whe
    0.75
     whee
    0.60
    whe
    0.53
    ніципа
    0.49
     Whelan
    0.48
    gemeen
    0.46
    ̍
    0.45
    treas
    0.44
    Nicely
    0.43
    Activations Density 0.026%

    No Known Activations