© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 108
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions of qualifications

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

    after "that," "this," or predicate "does"

    np_acts-logits-general · gemini-2.0-flash

    does or doesn't statements

    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
    renar
    -0.52
     lacked
    -0.51
     unregistered
    -0.50
     nonexistent
    -0.49
    endpush
    -0.49
    DoubleQuotes
    -0.49
    eless
    -0.47
    堪
    -0.47
    fromUtf
    -0.47
     unseen
    -0.47
    POSITIVE LOGITS
     doesn
    1.49
     does
    1.31
     Doesn
    1.29
    doesn
    1.27
    Doesn
    1.20
    does
    1.15
    Does
    1.13
     doesnt
    1.09
     Does
    1.09
    DOES
    1.02
    Activations Density 0.227%

    No Known Activations