© 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. 86694
    Prev
    Next
    INDEX
    Explanations

    functions and operations related to data processing and reduction

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

    accumulation and aggregation

    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
     kasarigan
    -0.98
     queſta
    -0.94
    :✨
    -0.81
     يتيمه
    -0.79
     للاسماء
    -0.74
    Географиясе
    -0.73
     الحره
    -0.72
    FunctionFlags
    -0.69
    Personensuche
    -0.68
     Waſſer
    -0.67
    POSITIVE LOGITS
    reduce
    0.73
    Reduce
    0.50
     reduce
    0.50
     sum
    0.46
     Reduce
    0.45
    Reducer
    0.41
    readFileSync
    0.41
     combineReducers
    0.41
    sum
    0.39
     réduire
    0.35
    Activations Density 0.005%

    No Known Activations