© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 8769
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical positions or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liosis
    -0.64
    нига
    -0.63
    водства
    -0.59
    ArrowToggle
    -0.58
    wości
    -0.58
     HasFactory
    -0.58
    uples
    -0.56
    Linki
    -0.55
     Lakers
    -0.55
    tanooga
    -0.55
    POSITIVE LOGITS
    Attention
    0.71
     Attention
    0.70
     ranks
    0.69
    Portail
    0.63
     ModelExpression
    0.60
    attention
    0.57
     affective
    0.56
     rank
    0.56
    twimg
    0.56
    λλη
    0.53
    Activations Density 0.057%

    No Known Activations