© 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. 19-GEMMASCOPE-RES-16K
    11. 520
    Prev
    Next
    INDEX
    Explanations

    mentions of Washington, D.C. and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setOnItem
    -0.71
     defaultstate
    -0.70
     مرئيه
    -0.64
     vPvB
    -0.64
    EIF
    -0.63
    orex
    -0.61
     createSlice
    -0.61
     heat
    -0.59
    abstractmethod
    -0.58
    WRP
    -0.58
    POSITIVE LOGITS
     Washington
    0.85
     DC
    0.83
    Washington
    0.78
     washington
    0.74
    ASHINGTON
    0.73
     Redskins
    0.73
     WASHINGTON
    0.72
    DC
    0.70
    WASHINGTON
    0.69
     ModelExpression
    0.68
    Activations Density 0.082%

    No Known Activations