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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 73640
    Prev
    Next
    INDEX
    Explanations

    technical terminology and programming constructs

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

    Code tokens, syntax elements, and technical terms that serve important functional roles in program structure or documentation.

    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
    richTextPanel
    -0.57
     AssemblyCulture
    -0.55
     समीक्षाओं
    -0.54
     transfieras
    -0.49
    twimg
    -0.48
     nahilalakip
    -0.46
    Diweddarwch
    -0.45
    GOTREF
    -0.45
    PerformLayout
    -0.45
    Przypisy
    -0.44
    POSITIVE LOGITS
     Lud
    0.47
    Lud
    0.47
    ----</
    0.43
     Anson
    0.42
     Spes
    0.42
     Dab
    0.41
    Spes
    0.41
    beau
    0.41
    醐
    0.40
    pakk
    0.40
    Activations Density 0.328%

    No Known Activations