© 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. 20-GEMMASCOPE-RES-131K
    11. 53174
    Prev
    Next
    INDEX
    Explanations

    terms related to bonus features in gaming contexts

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

    bonus features or rounds

    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
     الحره
    -0.62
    ambién
    -0.61
    pecabe
    -0.60
    MigrationBuilder
    -0.54
    ſelben
    -0.52
    jangkau
    -0.51
    duate
    -0.50
     tevreden
    -0.50
    erçe
    -0.50
     felicidade
    -0.50
    POSITIVE LOGITS
    ActionMode
    0.30
    Scénario
    0.28
    فایل‌لار
    0.28
     teat
    0.27
    ServiceTest
    0.27
     ModelExpression
    0.27
    serien
    0.27
    ☸
    0.27
    bustion
    0.26
     ✭✭
    0.25
    Activations Density 0.002%

    No Known Activations