© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    terms related to structured data and inquiry extraction

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

    Follows tokens like document, a, p, 2, toxic, or the

    np_acts-logits-general · gemini-2.0-flash

    toxic content parsing

    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
    gebühren
    -0.30
     prochaines
    -0.29
     at
    -0.29
     must
    -0.29
     here
    -0.28
     i
    -0.28
    ंदु
    -0.28
     head
    -0.28
     manhã
    -0.28
    .
    -0.27
    POSITIVE LOGITS
     betweenstory
    1.11
    parsedMessage
    0.81
     contextLoads
    0.73
     queſta
    0.69
     cherchés
    0.68
     Administrativna
    0.67
    GEBURTSDATUM
    0.67
    EDEFAULT
    0.67
    DeleteBehavior
    0.67
    
    0.66
    Activations Density 0.753%

    No Known Activations