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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99644
    Prev
    Next
    INDEX
    Explanations

    specific configuration settings related to response handling in API code

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

    API data entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.77
    ↵
    -0.73
      
    -0.73
    <eos>
    -0.71
    ,
    -0.71
     (
    -0.69
    '
    -0.69
    -
    -0.68
     
    -0.65
    (
    -0.60
    POSITIVE LOGITS
     autorytatywna
    3.33
    Personendaten
    2.94
    rungsseite
    2.89
    GEBURTSDATUM
    2.81
    Autoritní
    2.81
    parsedMessage
    2.72
     disambiguazione
    2.66
    Personensuche
    2.66
    MigrationBuilder
    2.64
    Билгалдахарш
    2.61
    Activations Density 0.003%

    No Known Activations