© 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. 11625
    Prev
    Next
    INDEX
    Explanations

    modals and verbs indicating potential or possibility

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

    "Can" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    possibility or occurrence

    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
    writeFieldEnd
    -0.71
    +#+#
    -0.64
    probably
    -0.58
    ThroughAttribute
    -0.56
    webElementXpaths
    -0.56
    presumably
    -0.56
     Probably
    -0.53
    necessarily
    -0.53
    多分
    -0.52
    Probably
    -0.52
    POSITIVE LOGITS
     sometimes
    1.11
     ibland
    0.96
    sometimes
    0.90
     Sometimes
    0.88
    有时候
    0.86
    Sometimes
    0.86
     durchaus
    0.85
     бывает
    0.85
     parfois
    0.84
     бывают
    0.82
    Activations Density 0.387%

    No Known Activations