© 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. 14739
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives conveying substantial magnitude or intensity

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

    large size or scale

    np_acts-logits-general · gemini-2.0-flash

    vastness and intensity

    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
    setDo
    -0.56
    +#+#
    -0.48
    LayoutStyle
    -0.47
     GetEnumerator
    -0.44
    rungsseite
    -0.40
     jambe
    -0.40
     formality
    -0.40
    ⓧ
    -0.40
     senare
    -0.40
     förslag
    -0.39
    POSITIVE LOGITS
     huge
    0.91
    huge
    0.91
     enormous
    0.90
    ormous
    0.86
     HUGE
    0.86
    Huge
    0.84
     Huge
    0.84
     tremendous
    0.84
     incredibly
    0.83
     enorme
    0.81
    Activations Density 0.124%

    No Known Activations