© 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. 22-GEMMASCOPE-RES-16K
    11. 5130
    Prev
    Next
    INDEX
    Explanations

    words that convey a sense of intensity or approximation, particularly the adverb "pretty."

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

    Followed by "much" or "sure"

    np_acts-logits-general · gemini-2.0-flash

    pretty much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.51
    ために
    -0.50
    〈
    -0.47
     كمان
    -0.47
     davantage
    -0.46
    為に
    -0.45
    IsContent
    -0.45
    évaluateur
    -0.45
    ítja
    -0.45
    <h1>
    -0.45
    POSITIVE LOGITS
     darn
    1.14
     much
    1.03
     damn
    0.92
    much
    0.86
    Much
    0.86
     damned
    0.82
     Much
    0.79
     decent
    0.74
     dang
    0.71
     pretty
    0.68
    Activations Density 0.029%

    No Known Activations