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

    Neuronpedia

    Jacobian LensNEW
    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. 15105
    Prev
    Next
    INDEX
    Explanations

    references to updates and future actions regarding information dissemination

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

    Following words related to updates or information

    np_acts-logits-general · gemini-2.0-flash

    news and announcements

    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
    ########.
    -0.65
     فريبيس
    -0.58
     autorytatywna
    -0.57
    PointerException
    -0.56
    +:+
    -0.56
    CPtr
    -0.55
    OGND
    -0.54
    rrggbb
    -0.54
    $_['
    -0.54
    Tracce
    -0.54
    POSITIVE LOGITS
     updates
    0.43
     announcements
    0.40
     news
    0.36
     newsletter
    0.36
    ข่าว
    0.34
     coming
    0.34
     newsletters
    0.31
     releases
    0.31
     follow
    0.30
     daily
    0.30
    Activations Density 0.106%

    No Known Activations