© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 34397
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting in code snippets

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    джан
    -0.46
     defaultstate
    -0.40
    glLoad
    -0.38
     Vivi
    -0.38
     chi
    -0.38
     Chi
    -0.38
    askar
    -0.37
     lượt
    -0.36
    agan
    -0.36
     hu
    -0.36
    POSITIVE LOGITS
    HideFlags
    0.58
    sizeCache
    0.56
     način
    0.54
    MessageOf
    0.54
     nakalista
    0.52
    rungsseite
    0.51
     dalamnya
    0.50
    AutoScaleMode
    0.49
     zelve
    0.49
    دانشنامهٔ
    0.48
    Activations Density 0.000%

    No Known Activations