© 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. 12-GEMMASCOPE-RES-16K
    11. 13188
    Prev
    Next
    INDEX
    Explanations

    details related to architectural features and the ambiance of locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMID
    -0.37
    ༘
    -0.33
    toHaveBeenCalled
    -0.32
     sentido
    -0.32
    ieteur
    -0.32
     sartén
    -0.31
     ITIS
    -0.30
    gesch
    -0.30
    oweit
    -0.30
    siella
    -0.30
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    Personendaten
    0.65
    rungsseite
    0.57
    parsedMessage
    0.55
    Tembelea
    0.54
     ExecuteAsync
    0.53
     beautifully
    0.51
    ViewImports
    0.47
     beautiful
    0.47
     صوتيه
    0.46
    Activations Density 0.258%

    No Known Activations