© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    references to previously mentioned or stated information in the text

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

    like "said," "mentioned," or "indicated"

    np_acts-logits-general · gemini-2.0-flash

    referring to previous statements

    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
     Co
    -0.33
    devServer
    -0.32
     Br
    -0.31
    Co
    -0.31
    Desktop
    -0.31
    gew
    -0.29
     media
    -0.29
     réuss
    -0.29
    Tv
    -0.28
    userLogin
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.77
    tanleria
    0.77
    ніципалі
    0.76
    Geplaatst
    0.75
    PreferredItem
    0.74
    ConstraintMaker
    0.72
    
    0.66
    hyrchwyd
    0.66
    kháu
    0.65
    +#+#
    0.64
    Activations Density 0.362%

    No Known Activations