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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9636
    Prev
    Next
    INDEX
    Explanations

    mathematical operations involving multiplication and specificity in numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     <<<<<<<<<<<<<<
    -0.57
     only
    -0.48
    Джерела
    -0.48
    Erreferentziak
    -0.48
    Примечания
    -0.47
    Bibliographie
    -0.45
    Cyfeiriadau
    -0.45
    슷
    -0.43
    OrBuilder
    -0.42
    '
    -0.41
    POSITIVE LOGITS
    +#+#
    0.98
    évaluateur
    0.83
     disambiguazione
    0.81
    لاعات
    0.73
    Xna
    0.69
    ELTS
    0.68
    MessageOf
    0.68
    bootstrapcdn
    0.67
     opérateur
    0.66
    ScopeManager
    0.66
    Activations Density 0.963%

    No Known Activations