© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 306
    Prev
    Next
    INDEX
    Explanations

    keywords related to program control flow and response handling

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

    elements related to control flow and result handling in programming code

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

    legal judgment as

    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
    archiviato
    -0.50
    তথ্যসূত্র
    -0.49
     layui
    -0.46
    terraform
    -0.46
    astéroïdes
    -0.44
     kayna
    -0.44
    endif
    -0.43
    KommentareTeilen
    -0.42
    ாத
    -0.42
    zwald
    -0.41
    POSITIVE LOGITS
     GenerationType
    0.85
     CURIAM
    0.71
    WindowConstants
    0.68
     الحره
    0.67
    ContentAsync
    0.58
    twimg
    0.56
    Données
    0.56
     groupBox
    0.55
    calipsis
    0.55
    criminator
    0.54
    Activations Density 0.017%

    No Known Activations