© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104509
    Prev
    Next
    INDEX
    Explanations

    references to comic strips and their creators

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

    References to comic strips, cartoons, and their creators in publishing or descriptive contexts.

    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
    audiovisuel
    -0.44
     propOrder
    -0.43
    DockStyle
    -0.40
    DecimalFormat
    -0.40
    DotNetBar
    -0.39
    elemField
    -0.38
    UrlResolution
    -0.38
     للمعارف
    -0.37
    rungsseite
    -0.37
    eseorang
    -0.36
    POSITIVE LOGITS
    httphttps
    0.55
    
    0.46
    UserScript
    0.44
     comics
    0.44
     Markup
    0.44
     تانيه
    0.43
    comics
    0.43
     Comics
    0.42
    Comics
    0.42
     ویکی‌آمباردا
    0.42
    Activations Density 0.015%

    No Known Activations