© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39583
    Prev
    Next
    INDEX
    Explanations

    variations of the word "craft" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.78
     Seton
    -0.75
    AttributeSet
    -0.75
    //
    -0.69
     Kidd
    -0.68
    HttpHeaders
    -0.67
     MEP
    -0.67
    schild
    -0.67
    toPromise
    -0.67
     Linton
    -0.66
    POSITIVE LOGITS
    Cra
    1.41
     CRA
    1.38
     Cra
    1.32
    cra
    1.28
     Cramer
    1.26
     cra
    1.23
     Craven
    1.20
     KRA
    1.19
     Kra
    1.17
     kra
    1.13
    Activations Density 0.009%

    No Known Activations