© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64066
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and references related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    <start_of_turn>user

    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
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -0.37
    Pozdrawiam
    -0.36
     Messina
    -0.35
    freude
    -0.35
    colorbar
    -0.35
     Wohn
    -0.34
    ,
    -0.33
    interopRequire
    -0.33
     Mercier
    -0.33
    ↵
    -0.32
    POSITIVE LOGITS
    tvguidetime
    0.72
    ésultats
    0.70
    protoimpl
    0.65
    iſen
    0.65
    ſcher
    0.65
    TypedDataSet
    0.65
     ujednoznacz
    0.62
    ſchaft
    0.61
    mybatisplus
    0.60
     JpaRepository
    0.58
    Activations Density 0.000%

    No Known Activations