© 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. 11-GEMMASCOPE-RES-16K
    11. 6477
    Prev
    Next
    INDEX
    Explanations

    sports-related terminology, specifically in the context of cricket

    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
    HandlerContext
    -0.48
    Region
    -0.47
     trajets
    -0.41
     por
    -0.41
    cain
    -0.39
     mexicanos
    -0.38
     Region
    -0.38
     my
    -0.38
    mappedBy
    -0.37
    art
    -0.37
    POSITIVE LOGITS
    enumii
    0.98
    mybatisplus
    0.95
    WireFormatLite
    0.89
    IsPostBack
    0.89
     myſelf
    0.83
    CloseOperation
    0.81
     AssemblyCulture
    0.81
    ]")]
    0.80
     itſelf
    0.80
     Anſ
    0.79
    Activations Density 0.056%

    No Known Activations