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. 114887
    Prev
    Next
    INDEX
    Explanations

    identifiers related to sports rankings and match statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     conoció
    -0.54
     vorstellen
    -0.53
    ulongan
    -0.52
     entiende
    -0.52
     afectado
    -0.50
     obligado
    -0.50
     bekijken
    -0.49
     afectada
    -0.49
     EconPapers
    -0.49
     achtergrond
    -0.49
    POSITIVE LOGITS
     Meksiku
    0.48
    <?
    0.45
    DockStyle
    0.42
    Revenir
    0.42
    keyColumn
    0.39
    #
    0.38
    fetchone
    0.38
     المعيارى
    0.36
    LikeLike
    0.36
    ฯ
    0.36
    Activations Density 0.005%

    No Known Activations