© 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. 72996
    Prev
    Next
    INDEX
    Explanations

    the end of a section or document

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

    end of a structured block

    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
     otomatig
    -1.00
    SharedDtor
    -0.88
    脚注の使い方
    -0.88
     '\\;'
    -0.83
    hoeddwyd
    -0.80
     PeEnEo
    -0.79
     Chwiliwch
    -0.79
     disambiguazione
    -0.77
    parsedMessage
    -0.75
    CppMethod
    -0.74
    POSITIVE LOGITS
    <eos>
    0.39
     respectivamente
    0.37
    ↵↵↵
    0.35
    ↵↵↵↵
    0.35
     respectivement
    0.34
    ↵↵
    0.29
    ตรี
    0.29
    section
    0.29
     respectively
    0.29
     состав
    0.28
    Activations Density 0.008%

    No Known Activations