© 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. 111880
    Prev
    Next
    INDEX
    Explanations

    specific nouns and expressions related to families and key entities in various contexts

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

    analyzing statistics or programming

    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
     Rij
    -0.35
    Rij
    -0.35
    Mt
    -0.34
     bug
    -0.32
     deliberately
    -0.31
     uds
    -0.31
     arriving
    -0.31
     arrived
    -0.30
    inven
    -0.30
     drum
    -0.30
    POSITIVE LOGITS
     الرياضيه
    0.93
    RTLR
    0.79
    adaptiveStyles
    0.77
     informée
    0.68
     autorytatywna
    0.67
    onActivityResult
    0.66
    AccessorTable
    0.64
    әрмәләр
    0.63
     للمعارف
    0.62
    InjectAttribute
    0.61
    Activations Density 0.000%

    No Known Activations