© 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. 9204
    Prev
    Next
    INDEX
    Explanations

    references to alternatives or additional options in various contexts

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

    following "other" or "also"

    np_acts-logits-general · gemini-2.0-flash

    other or alternative

    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
    ValueStyle
    -0.56
    เคร
    -0.44
     silikon
    -0.35
    pragma
    -0.34
     loops
    -0.34
     jó
    -0.33
    ärna
    -0.33
     sampel
    -0.33
    AndEndTag
    -0.33
     dày
    -0.33
    POSITIVE LOGITS
     ویکی‌پدیا
    0.62
     ProtoMessage
    0.59
    devamını
    0.59
    
    0.59
    contentLoaded
    0.56
     mergeFrom
    0.55
     kaarangay
    0.54
    dflare
    0.53
    GEBURTSDATUM
    0.52
     Infórmanos
    0.52
    Activations Density 0.719%

    No Known Activations