© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11633
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to social or economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     незавершена
    -0.86
     surla
    -0.81
     виправивши
    -0.76
    Tikang
    -0.76
    expandindo
    -0.72
    parsedMessage
    -0.68
     AssemblyCulture
    -0.68
    rawDesc
    -0.67
    providedIn
    -0.66
     utafitiHapana
    -0.65
    POSITIVE LOGITS
    хь
    0.36
     poorer
    0.29
     disproportion
    0.28
     groups
    0.27
     taux
    0.26
     grupos
    0.26
     Bok
    0.25
     tendenza
    0.25
     moyenne
    0.24
     ücret
    0.24
    Activations Density 0.644%

    No Known Activations