© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1477
    Prev
    Next
    INDEX
    Explanations

    structures or patterns that involve repeated elements or placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    placeholder elements or markers in a coding or markup context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.83
    Демографія
    -0.72
     FetchType
    -0.70
    setObjectName
    -0.66
     resourceCulture
    -0.65
    endphp
    -0.65
    CPtr
    -0.64
     autorytatywna
    -0.62
     AssemblyTitle
    -0.61
    bibitem
    -0.61
    POSITIVE LOGITS
    <
    0.57
     africains
    0.56
     obsidian
    0.51
    </
    0.51
     withal
    0.49
     Debussy
    0.49
    帖最后由
    0.48
     Pompey
    0.48
     Abidjan
    0.47
     Solon
    0.47
    Activations Density 0.047%

    No Known Activations