© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 1351
    Prev
    Next
    INDEX
    Explanations

    informative and analytical discussions related to medical or psychological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multil
    -0.52
     rhestr
    -0.52
     propOrder
    -0.50
     auroit
    -0.48
    Autoritní
    -0.47
     persu
    -0.47
     endwhile
    -0.47
    agerie
    -0.47
     incons
    -0.46
     rhetor
    -0.45
    POSITIVE LOGITS
    bcryptjs
    0.37
    imbawa
    0.35
     beelden
    0.34
     programu
    0.34
    pectiva
    0.33
    iële
    0.33
    vestimento
    0.30
    GMENT
    0.30
     im
    0.30
     صور
    0.30
    Activations Density 0.200%

    No Known Activations