© 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. 9-GEMMASCOPE-RES-16K
    11. 5778
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt, uncertainty, or contemplation

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

    Interjections like "hmm", "ouch", and "wow"

    np_acts-logits-general · gemini-2.0-flash

    interjections and exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.67
    __":
    -0.64
    :✨
    -0.60
     estekak
    -0.59
    Ӕ
    -0.57
     INTERESAR
    -0.56
    __":
    -0.55
    WEBPACK
    -0.54
    __':
    -0.53
    Välislingid
    -0.50
    POSITIVE LOGITS
    Wow
    0.91
     Wow
    0.90
     wow
    0.85
    Whoa
    0.77
    Hmm
    0.77
    Oops
    0.76
    wow
    0.75
     Hmm
    0.75
    Huh
    0.75
     WOW
    0.75
    Activations Density 0.364%

    No Known Activations