© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1420
    Prev
    Next
    INDEX
    Explanations

    specific criteria and requirements related to applications and evaluations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    names, details, or information requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    EDEFAULT
    -0.38
     despe
    -0.34
     under
    -0.34
     pledging
    -0.34
    pieler
    -0.33
    WriteLiteral
    -0.33
     Tal
    -0.32
     break
    -0.32
     restore
    -0.31
     Erskine
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.88
     Offisielt
    0.63
    IntoConstraints
    0.62
     autorytatywna
    0.61
    StoryboardSegue
    0.59
     MainAxisSize
    0.57
    SourceChecksum
    0.56
    pannt
    0.56
     الحره
    0.55
     يتيمه
    0.55
    Activations Density 0.033%

    No Known Activations