© 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. 31-GEMMASCOPE-RES-16K
    11. 2996
    Prev
    Next
    INDEX
    Explanations

    specific formal structures and terms used in mathematical or legal contexts

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

    enumerated lists and numbered reference points in formal documents.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     unknownFields
    -0.48
    uxxxx
    -0.47
    Personensuche
    -0.46
     DbSet
    -0.42
     препратки
    -0.38
    zzleHttp
    -0.38
    principalTable
    -0.37
     &___
    -0.35
    inSlope
    -0.35
     utafitiHapana
    -0.34
    POSITIVE LOGITS
     item
    0.98
     bullet
    0.96
     пункт
    0.89
     пунк
    0.83
     Item
    0.82
     bullets
    0.79
    ข้อ
    0.79
     items
    0.79
     point
    0.77
    Item
    0.77
    Activations Density 0.833%

    No Known Activations