© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13288
    Prev
    Next
    INDEX
    Explanations

    affirmations or confirmations in conversation

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

    Follows "ok", "okay", or "now"

    np_acts-logits-general · gemini-2.0-flash

    acknowledgement and transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Билгалдахарш
    -0.42
    inSlope
    -0.36
     victims
    -0.36
     Victims
    -0.35
     commento
    -0.35
     zvuky
    -0.35
    Produzione
    -0.35
     hohen
    -0.35
     mortality
    -0.35
    Купить
    -0.35
    POSITIVE LOGITS
    routeProvider
    0.56
    matchCondition
    0.54
    Итак
    0.52
    Now
    0.51
    TestingModule
    0.51
    UnknownFields
    0.49
     contextLoads
    0.47
    gendes
    0.46
    setupUi
    0.46
    prefixer
    0.45
    Activations Density 0.179%

    No Known Activations