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. 6713
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical expressions used in advanced equations

    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
    تقاوى
    -0.79
     Roskov
    -0.71
     VIAF
    -0.65
     Wikimedijinoj
    -0.61
     Wikispecies
    -0.61
     prot
    -0.60
    хьтан
    -0.58
    IndentedString
    -0.58
    IntoConstraints
    -0.56
    IGraphics
    -0.55
    POSITIVE LOGITS
     ثابت
    0.52
    何より
    0.50
     backlash
    0.49
     נוספת
    0.48
     gammal
    0.47
     two
    0.47
    ResourceBundle
    0.47
    itados
    0.46
    #
    0.46
    boru
    0.46
    Activations Density 2.383%

    No Known Activations