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. 40783
    Prev
    Next
    INDEX
    Explanations

    references to classification and membership in programming or organizational contexts

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

    Common components or elements in technical contexts, typically referring to structural items (file modes, class structures), connective phrases in procedural instructions, and technical terms within specialized subject matter.

    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
     featured
    -0.34
     itemprop
    -0.33
    Skocz
    -0.31
     soft
    -0.31
     sweet
    -0.30
     far
    -0.30
    ierto
    -0.29
     overrated
    -0.29
    ự
    -0.29
     answer
    -0.28
    POSITIVE LOGITS
    Vidite
    0.75
     uusi
    0.68
     Additions
    0.66
    Ӕ
    0.66
     المعيارى
    0.66
     additions
    0.61
    Additions
    0.60
     nuevos
    0.60
     nowych
    0.59
     nových
    0.59
    Activations Density 0.147%

    No Known Activations