© 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. 72839
    Prev
    Next
    INDEX
    Explanations

    large amounts of whitespace and formatting characters

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

    code markup syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    parametrize
    -0.43
     ever
    -0.42
    NUMERIC
    -0.39
    ↵↵
    -0.38
    hal
    -0.36
     πο
    -0.35
     Mar
    -0.35
     Baran
    -0.35
     tend
    -0.35
    というと
    -0.35
    POSITIVE LOGITS
     noDo
    0.72
    Personendaten
    0.67
    expandindo
    0.66
     Савезне
    0.63
    Geplaatst
    0.61
     disambiguazione
    0.60
    ⤹
    0.59
    tvguidetime
    0.58
    
    0.57
     ujednoznacz
    0.57
    Activations Density 0.003%

    No Known Activations