© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13559
    Prev
    Next
    INDEX
    Explanations

    various programming syntax elements, specifically around function parameters and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.75
    providedIn
    -0.62
     justement
    -0.56
    Wut
    -0.55
    iritto
    -0.54
     NSCoder
    -0.54
     étant
    -0.52
     Whist
    -0.51
     Ciò
    -0.51
     newVal
    -0.51
    POSITIVE LOGITS
    +"&
    0.69
    :✨
    0.69
    &__
    0.62
    InitVars
    0.61
    bekah
    0.61
    MigrationBuilder
    0.58
    ,:),
    0.58
    StoreMessageInfo
    0.58
     %>%
    0.57
    urgy
    0.56
    Activations Density 0.094%

    No Known Activations