© 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. 3-GEMMASCOPE-RES-16K
    11. 10007
    Prev
    Next
    INDEX
    Explanations

    references to garage doors and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livrer
    -0.77
     fallu
    -0.77
    lapsible
    -0.75
    lijn
    -0.72
     livré
    -0.70
     Karn
    -0.69
    seamnă
    -0.68
    llong
    -0.67
    hésite
    -0.66
    liness
    -0.65
    POSITIVE LOGITS
     يتيمه
    0.89
    GEBURTSDATUM
    0.83
     regret
    0.81
     layui
    0.79
    rungsseite
    0.73
    WebElementEntity
    0.70
     regrets
    0.70
    CloseOperation
    0.70
     disambiguazione
    0.70
    [--
    0.70
    Activations Density 0.057%

    No Known Activations