© 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. 15-GEMMASCOPE-RES-16K
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    the presence of the start of new sections or topics in a document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     виправивши
    -0.48
     propOrder
    -0.43
    例句
    -0.40
    tonode
    -0.38
     Италијани
    -0.36
    новништво
    -0.36
    <eos>
    -0.35
     سكانية
    -0.35
    Spoljašnje
    -0.35
    drawSprites
    -0.34
    POSITIVE LOGITS
     esternos
    0.57
     Anſ
    0.57
     parallax
    0.56
     ་་
    0.55
     يتيمه
    0.55
     denom
    0.54
     myſelf
    0.54
    征詢我
    0.54
     endian
    0.54
    ſtance
    0.53
    Activations Density 0.055%

    No Known Activations