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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7446
    Prev
    Next
    INDEX
    Explanations

    phrases related to mixed methods or combinations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.70
    }{*}{
    -0.67
    </tfoot>
    -0.58
    defaultProps
    -0.55
    ](#
    -0.52
     almendras
    -0.52
    henden
    -0.51
     calorías
    -0.51
    struzioni
    -0.51
    Bism
    -0.51
    POSITIVE LOGITS
     MIX
    1.16
    MIX
    1.04
     mix
    1.03
     mixes
    1.02
     Mix
    1.01
    Mix
    0.94
    mix
    0.94
     mixtures
    0.90
     mingle
    0.86
     mixt
    0.85
    Activations Density 0.060%

    No Known Activations