© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 83260
    Prev
    Next
    INDEX
    Explanations

    classes related to data parsing or object transformation

    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 @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemId
    -1.07
    CloseOperation
    -0.66
    الحياه
    -0.63
    OutputType
    -0.60
     ModelExpression
    -0.56
    HasAnnotation
    -0.52
    ToBounds
    -0.51
    ፩
    -0.49
    ษัท
    -0.49
     PyTuple
    -0.49
    POSITIVE LOGITS
    Seeder
    3.55
     Seeder
    1.28
     seed
    0.81
     Seed
    0.71
    Seed
    0.70
     SEED
    0.67
     seeding
    0.66
     seeds
    0.63
    seed
    0.62
     seeded
    0.62
    Activations Density 0.000%

    No Known Activations