© 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. 12314
    Prev
    Next
    INDEX
    Explanations

    terms related to maximum values and efficiency metrics in various contexts

    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
    enterOuterAlt
    -0.42
    pecting
    -0.40
    Respectfully
    -0.40
     sitten
    -0.39
    gründung
    -0.38
     computadora
    -0.38
    devším
    -0.38
     manipulation
    -0.37
     venant
    -0.37
    Przypisy
    -0.37
    POSITIVE LOGITS
    EDEFAULT
    0.70
     average
    0.66
    Average
    0.62
    平均
    0.60
     Average
    0.59
     minimum
    0.57
    Minimum
    0.56
     AVERAGE
    0.56
     Minimum
    0.55
    average
    0.55
    Activations Density 1.281%

    No Known Activations