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. 117277
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and specific political or social incidents

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

    Geographic locations, organizational acronyms, and fragments of dates or identifiers that appear in formal or technical 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
     esternos
    -0.46
     المعيارى
    -0.45
    ukone
    -0.44
    niająca
    -0.44
    :✨
    -0.42
    enumii
    -0.42
     inalámbrica
    -0.42
    Autoritní
    -0.41
    URLException
    -0.40
     mecánico
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.54
    saraba
    0.52
    PreferredItem
    0.46
    IndentedString
    0.45
    GEBURTSDATUM
    0.44
     vulgares
    0.41
     Winaray
    0.41
     titular
    0.40
     Daß
    0.39
    thâu
    0.39
    Activations Density 0.180%

    No Known Activations