© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 15972
    Prev
    Next
    INDEX
    Explanations

    titles of movies and series, particularly those in the action or superhero genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.76
    WireFormatLite
    -0.73
    الحياه
    -0.70
    expandindo
    -0.70
     فريبيس
    -0.68
    RegistryLite
    -0.68
     StatelessWidget
    -0.67
     يتيمه
    -0.67
    ⓧ
    -0.65
    pushFollow
    -0.63
    POSITIVE LOGITS
    setVerticalGroup
    0.61
    󠁿
    0.55
    Trail
    0.49
    レーション
    0.48
    trail
    0.46
    CodeAttribute
    0.44
     합니다
    0.43
    HasColumnName
    0.43
     trail
    0.42
     sonnen
    0.42
    Activations Density 0.205%

    No Known Activations