© 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. 7951
    Prev
    Next
    INDEX
    Explanations

    the presence of pronouns and references to individuals in a context related to political campaigning or decision-making

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

    Tokens preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    pronoun then modal verb

    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
     going
    -0.59
     a
    -0.59
     is
    -0.57
     expected
    -0.56
     See
    -0.54
     be
    -0.54
     
    -0.54
     get
    -0.53
     been
    -0.53
    是
    -0.53
    POSITIVE LOGITS
    Datuak
    1.16
    Życiorys
    1.13
    ValueStyle
    1.09
    Билгалдахарш
    1.06
    AccessorTable
    1.04
    setVerticalGroup
    1.04
    tagHelperRunner
    1.04
     للاسماء
    1.03
    KommentareTeilen
    1.02
    UnusedPrivate
    1.00
    Activations Density 0.348%

    No Known Activations