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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7694
    Prev
    Next
    INDEX
    Explanations

    elements related to database operations and date handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shaker
    -0.35
    usky
    -0.34
    Искәрмәләр
    -0.34
     Kers
    -0.34
     dimensionless
    -0.34
     shaker
    -0.34
     columna
    -0.34
    Venice
    -0.33
     zbo
    -0.33
     transférez
    -0.33
    POSITIVE LOGITS
     MongoDB
    0.90
     mongodb
    0.81
     Mongo
    0.81
     mongo
    0.77
    MongoDB
    0.77
     bson
    0.77
     pymongo
    0.75
     ObjectId
    0.75
    Mongo
    0.74
     Mongolian
    0.71
    Activations Density 0.168%

    No Known Activations