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. 2953
    Prev
    Next
    INDEX
    Explanations

    references to penalties and physical actions in sports 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
     Roskov
    -0.60
    asztal
    -0.54
    tagHelperRunner
    -0.53
     Klicken
    -0.51
    āng
    -0.49
     experiments
    -0.48
     الاطلاع
    -0.47
    rung
    -0.47
     gostar
    -0.47
    轰隆隆
    -0.47
    POSITIVE LOGITS
     blocking
    0.64
    Blocking
    0.60
    出版年
    0.59
    __*/
    0.56
    }}/>
    0.56
     defender
    0.55
     contact
    0.55
    blocking
    0.55
     blockers
    0.55
     Scramble
    0.55
    Activations Density 0.169%

    No Known Activations