© 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. 31-GEMMASCOPE-RES-131K
    6. 21597
    Prev
    Next
    INDEX
    Explanations

    calculations and probabilities related to choosing items without replacement

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

    probability of picking

    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
    ########.
    -0.72
     ProtoMessage
    -0.71
     EconPapers
    -0.69
     transfieras
    -0.68
     nonUne
    -0.64
     Infórmanos
    -0.64
     gyhoeddwyd
    -0.63
     ویکی‌پدی
    -0.62
    󠁴
    -0.61
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
     luck
    0.82
     lucky
    0.82
     unlucky
    0.74
     LUCK
    0.68
    lucky
    0.65
     randomly
    0.62
    运气
    0.60
    Lucky
    0.58
    random
    0.57
     random
    0.57
    Activations Density 0.049%

    No Known Activations