© 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. 27-GEMMASCOPE-RES-16K
    11. 12569
    Prev
    Next
    INDEX
    Explanations

    code snippets related to graphical user interface (GUI) elements and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.52
     ContentValues
    -0.51
    ſelf
    -0.49
     Houſe
    -0.48
    ########.
    -0.48
     AssemblyTitle
    -0.47
    ſelves
    -0.46
     ModelExpression
    -0.46
    AnimationFrame
    -0.46
     whiteColor
    -0.45
    POSITIVE LOGITS
     button
    1.45
    button
    1.29
    ボタン
    1.17
     buttons
    1.17
    Button
    1.16
     Button
    1.16
     BUTTON
    1.09
     botón
    1.09
     버튼
    1.07
    BUTTON
    1.03
    Activations Density 0.326%

    No Known Activations