© 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. 1307
    Prev
    Next
    INDEX
    Explanations

    numeric values and references throughout the text

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

    numerical data associated with file references or documentation

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

    years and numbers

    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
    ExtendWith
    -0.62
    VIAF
    -0.61
    下载附件
    -0.60
     transfieras
    -0.59
    WindowConstants
    -0.57
    slidesToShow
    -0.54
    drawal
    -0.54
    UnusedPrivate
    -0.53
    ympto
    -0.52
    SupportActionBar
    -0.50
    POSITIVE LOGITS
     snippetHide
    0.69
    Jeografia
    0.69
    ArrowToggle
    0.66
    TagHelper
    0.66
    tvguidetime
    0.63
     Biôgrafia
    0.61
    2
    0.60
    vatar
    0.56
    PreferredItem
    0.56
     jspb
    0.56
    Activations Density 0.152%

    No Known Activations