© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13721
    Prev
    Next
    INDEX
    Explanations

    categories and references related to documents and external links

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

    Text preceding external links and categories

    np_acts-logits-general · gemini-2.0-flash

    document links

    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
     IFTT
    -0.52
     iprot
    -0.48
    حياته
    -0.48
    ⟬
    -0.48
    ptid
    -0.47
    ulemon
    -0.47
     $("<
    -0.47
    styleable
    -0.46
    ReusableCell
    -0.44
    Билгалдахарш
    -0.44
    POSITIVE LOGITS
    <eos>
    0.72
     tartalomajánló
    0.64
     RISERVATA
    0.56
     Wikispecies
    0.49
     ویکی‌آمباردا
    0.49
    UnifiedTopology
    0.45
     ostavi
    0.45
     Réponses
    0.44
    </table>
    0.44
    StateToProps
    0.43
    Activations Density 0.019%

    No Known Activations