Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117367
    Prev
    Next
    INDEX
    Explanations

    terms related to streaming data and handling large files in programming contexts

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

    Technical terms related to data processing in code, particularly involving streaming or on-the-fly operations where data is processed incrementally rather than loaded entirely into memory.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     بغ
    -0.35
    adaptiveStyles
    -0.33
    bunda
    -0.30
    INCREF
    -0.30
    uga
    -0.29
     ​​
    -0.29
    Coordonnées
    -0.28
     berk
    -0.28
    ​​
    -0.28
     backyard
    -0.28
    POSITIVE LOGITS
    IntoConstraints
    0.94
    FieldBuilder
    0.57
    posedge
    0.56
    KURZBESCHREIBUNG
    0.55
     queſta
    0.54
    LEEP
    0.52
    tagext
    0.50
    modelBuilder
    0.49
    rawDesc
    0.49
    Espèce
    0.48
    Activations Density 0.236%

    No Known Activations