© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4592
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and their properties

    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
     onData
    -0.62
    StoryboardSegue
    -0.62
     useEffect
    -0.62
    RenderAtEndOf
    -0.62
    rungsseite
    -0.60
    Naw
    -0.60
     Naw
    -0.59
    AsStream
    -0.59
     FetchType
    -0.56
     Chá
    -0.55
    POSITIVE LOGITS
    mybatisplus
    0.73
     makeStyles
    0.71
    mui
    0.70
    ')));
    0.68
     ***!
    0.62
     DevComponents
    0.56
    DotNetBar
    0.56
    bootstrapcdn
    0.55
    antd
    0.54
    fhir
    0.53
    Activations Density 0.056%

    No Known Activations