© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "to" and related linguistic constructs

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

    the beginning of documents (the <bos> token).

    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
    CloseOperation
    -0.71
    +#+
    -0.71
    uxxxx
    -0.63
     firebaseConfig
    -0.60
    Newswire
    -0.56
    قایناقلار
    -0.56
    DriverManager
    -0.54
     jsPsych
    -0.53
     ſy
    -0.53
     absten
    -0.52
    POSITIVE LOGITS
     respectivas
    0.46
     consideración
    0.46
    TokenNameDOT
    0.42
     porción
    0.41
     bersifat
    0.41
     şeyler
    0.41
     Mitarbeit
    0.40
     činnosti
    0.39
     necesaria
    0.39
     utilización
    0.39
    Activations Density 1.988%

    No Known Activations