© 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. 10-GEMMASCOPE-RES-16K
    11. 7022
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "begin" and its variations, indicating it detects phrases that signal the start of different sections or elements within structured content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rungsseite
    -0.82
     AssemblyCulture
    -0.72
     esternos
    -0.68
     kaarangay
    -0.67
    Personensuche
    -0.66
     Италијани
    -0.66
    oa̍t
    -0.60
    Autoritní
    -0.60
     resourceCulture
    -0.60
    WithIOException
    -0.59
    POSITIVE LOGITS
    begin
    0.52
     FontWeight
    0.41
     Thir
    0.40
    <tbody>
    0.40
    ſtre
    0.39
    std
    0.36
    ╗
    0.35
    gira
    0.35
    juh
    0.35
    Begin
    0.34
    Activations Density 0.020%

    No Known Activations