© 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. 38670
    Prev
    Next
    INDEX
    Explanations

    words related to exploration and discovery of culinary experiences

    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
    IntoConstraints
    -0.60
     harshly
    -0.59
     ModelExpression
    -0.56
    ítmény
    -0.56
     Presley
    -0.55
    тистика
    -0.54
     helyzet
    -0.52
     stället
    -0.51
     larmes
    -0.51
     syndical
    -0.50
    POSITIVE LOGITS
     tartalomajánló
    0.75
     delightful
    0.69
     enjoyment
    0.68
     delights
    0.68
     enjoyable
    0.67
     adventurous
    0.67
     adventure
    0.67
     thrill
    0.66
     curious
    0.66
     curiosity
    0.65
    Activations Density 0.117%

    No Known Activations