© 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. 11741
    Prev
    Next
    INDEX
    Explanations

    expressions of political support or loyalty

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

    code, math, or non-English languages

    np_acts-logits-general · gemini-2.0-flash

    embracing all, is dead

    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
     дописавши
    -0.58
    libft
    -0.53
     freshest
    -0.50
    UrlResolution
    -0.48
    MANY
    -0.48
    Dys
    -0.48
    úgó
    -0.47
    ∖
    -0.47
    onete
    -0.46
     Dys
    -0.46
    POSITIVE LOGITS
    Diweddarwch
    0.42
     doInBackground
    0.41
     spiritual
    0.39
    DispatchToProps
    0.37
     SQLAlchemy
    0.36
     cuad
    0.34
     psychological
    0.33
    AccessFile
    0.33
    Lycka
    0.32
     muligt
    0.32
    Activations Density 0.075%

    No Known Activations