© 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. 38846
    Prev
    Next
    INDEX
    Explanations

    identifiers and structures related to datasets and data parameters

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

    datasets, dates, file, sales

    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
    ConstraintMaker
    -0.47
     caucho
    -0.35
     idéia
    -0.35
     vocación
    -0.35
     personalizada
    -0.34
     hidrá
    -0.34
    PostInfinity
    -0.34
     perfección
    -0.33
     personalización
    -0.33
     anfitrión
    -0.33
    POSITIVE LOGITS
     dataset
    0.97
     datasets
    0.87
     Dataset
    0.81
     data
    0.76
     newData
    0.76
     jsonData
    0.72
     Kag
    0.70
     betweenstory
    0.69
     dataframe
    0.69
    EndContext
    0.68
    Activations Density 0.101%

    No Known Activations