© 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. 16-GEMMASCOPE-RES-16K
    11. 12555
    Prev
    Next
    INDEX
    Explanations

    programming constructs or syntax patterns related to data structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    DeleteBehavior
    -0.45
    einander
    -0.33
     Aseg
    -0.30
     ква
    -0.26
     yü
    -0.26
    LElement
    -0.25
     clones
    -0.25
    Electric
    -0.25
    trá
    -0.24
    optim
    -0.24
    POSITIVE LOGITS
     resourceCulture
    0.82
    endphp
    0.69
     wireType
    0.68
    DotNetBar
    0.64
    +#+
    0.64
    ஧
    0.63
    parsedMessage
    0.63
    <unused68>
    0.63
    <unused14>
    0.63
    <unused8>
    0.63
    Activations Density 0.244%

    No Known Activations