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. 11-GEMMASCOPE-RES-16K
    6. 5920
    Prev
    Next
    INDEX
    Explanations

    structured data or information formatted in a specific way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iſt
    -0.81
     ―――――
    -0.79
     sánchez
    -0.78
     faſt
    -0.74
     ſche
    -0.72
     nú
    -0.71
     CHAPITRE
    -0.70
     staffel
    -0.68
    ly
    -0.68
     pegat
    -0.68
    POSITIVE LOGITS
     
    1.03
    zkopf
    0.73
    }{*}{}
    0.72
    󠁿
    0.71
    ↵
    0.65
    フェクト
    0.64
     vastaan
    0.63
    </em>
    0.62
    ség
    0.62
     Audiodateien
    0.62
    Activations Density 0.003%

    No Known Activations