© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6279
    Prev
    Next
    INDEX
    Explanations

    references to public health and safety measures

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

    words related to numerical data or specific quantities.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    intra-word punctuation, especially hyphens and apostrophes in contractions, possessives, and hyphenated terms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    Looking at the activations, the neuron strongly activates on common words in casual or conversational writing, particularly: - Articles ("a", "the") - Pronouns ("you", "we", "it") - Prepositions ("at", "of")

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    printStackTrace
    -0.34
    UrlResolution
    -0.33
     <>",
    -0.31
     onCreateView
    -0.28
     onBind
    -0.28
     starred
    -0.27
    FormatException
    -0.27
    retweeted
    -0.26
     ویکی‌پدیای
    -0.26
    jsonwebtoken
    -0.26
    POSITIVE LOGITS
     imagui
    0.68
    <unused23>
    0.67
    <unused41>
    0.66
    <unused8>
    0.66
    <unused47>
    0.66
    <unused79>
    0.66
    <unused52>
    0.66
    <unused80>
    0.66
    <pad>
    0.66
    [@BOS@]
    0.66
    Activations Density 0.432%

    No Known Activations