© 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. 35-GEMMASCOPE-RES-16K
    11. 10520
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to scripting and structured data in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GRect
    -0.41
    ↵↵
    -0.38
     vPvB
    -0.36
    IRQn
    -0.33
     Meksiku
    -0.31
    ::_('
    -0.31
    <eos>
    -0.30
     loob
    -0.29
    ंदु
    -0.29
    }></
    -0.29
    POSITIVE LOGITS
    Diweddarwch
    0.67
    IntoConstraints
    0.59
     للاسماء
    0.56
     estekak
    0.56
     linearized
    0.54
    Демографія
    0.54
     Roskov
    0.53
    ressible
    0.52
     CreateTagHelper
    0.52
    idual
    0.52
    Activations Density 0.053%

    No Known Activations