© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44201
    Prev
    Next
    INDEX
    Explanations

    references to data manipulation and database interactions

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

    seed or seeding

    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
    isContained
    -0.73
    UnusedPrivate
    -0.65
     ModelExpression
    -0.56
     المعيارى
    -0.56
     MainAxisSize
    -0.56
     صوتيه
    -0.55
    !*\
    -0.51
    .*")]
    -0.51
    ftagPool
    -0.50
    tagext
    -0.50
    POSITIVE LOGITS
    Seeder
    1.40
     seed
    1.07
     Seeder
    1.05
    Seed
    1.00
     Seed
    0.96
     seeds
    0.91
    seed
    0.91
     SEED
    0.81
     Seeds
    0.78
     seeding
    0.76
    Activations Density 0.001%

    No Known Activations