© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 12268
    Prev
    Next
    INDEX
    Explanations

    specific locations or events, particularly those related to geographical and temporal context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -0.66
    󠁣
    -0.65
     arşivlendi
    -0.64
     disambiguazione
    -0.64
     noDo
    -0.64
    complexContent
    -0.63
     ModelExpression
    -0.62
     estekak
    -0.62
    +#+#
    -0.62
    ंदीखरीदारी
    -0.62
    POSITIVE LOGITS
     nämlich
    0.44
     nemlig
    0.40
    werkers
    0.38
     bowiem
    0.38
    TokenNameLPAREN
    0.35
    ‌شده
    0.35
    mml
    0.34
    ณ์
    0.34
     Infatti
    0.34
     infatti
    0.34
    Activations Density 0.337%

    No Known Activations