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. 73509
    Prev
    Next
    INDEX
    Explanations

    references to the keyword "this" in various contexts

    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
     ujednoznacz
    -0.43
    <eos>
    -0.34
    Földrajz
    -0.32
    Và
    -0.32
     trône
    -0.31
    </tbody>
    -0.31
    Cuántos
    -0.29
     coloriage
    -0.29
    TypedDataSet
    -0.29
     élite
    -0.27
    POSITIVE LOGITS
     fashiola
    0.66
    tagHelperRunner
    0.60
    AddHtmlAttribute
    0.60
     للاسماء
    0.59
     createState
    0.59
    Hozzáférés
    0.59
    medriver
    0.58
    򐂰
    0.58
     メンテナ
    0.56
     パンチラ
    0.56
    Activations Density 0.009%

    No Known Activations