© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    mentions of inclusive events or organizations, particularly those labeled with "All" in their titles

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

    "All" followed by certain prepositions or possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    all followed by other words

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ViewFeatures
    -0.83
    EndInit
    -0.81
     snippetHide
    -0.70
    enumi
    -0.69
    AndEndTag
    -0.65
    KommentareTeilen
    -0.63
    HasForeignKey
    -0.61
    IVEREF
    -0.60
    unate
    -0.60
    EditorBrowsable
    -0.60
    POSITIVE LOGITS
     hail
    0.54
     perfons
    0.53
    ArgsConstructor
    0.50
    sizeCache
    0.49
     Hail
    0.49
     flav
    0.47
    About
    0.45
    Hail
    0.45
    rounder
    0.44
     makeStyles
    0.43
    Activations Density 0.080%

    No Known Activations