© 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. 14-GEMMASCOPE-RES-16K
    11. 5496
    Prev
    Next
    INDEX
    Explanations

    HTML table data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.78
     Inſ
    -0.72
    BagConstraints
    -0.68
    BagLayout
    -0.68
     ſy
    -0.65
    RenderAtEndOf
    -0.65
     feroit
    -0.64
    PerformLayout
    -0.60
    tvguidetime
    -0.60
     onPostExecute
    -0.59
    POSITIVE LOGITS
    <td>
    1.41
    <th>
    0.75
    __(/*!
    0.62
    ="
    0.60
    <h1>
    0.59
    <em>
    0.56
     a
    0.54
    <caption>
    0.52
    ("
    0.50
    <strong>
    0.49
    Activations Density 0.001%

    No Known Activations