© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 9596
    Prev
    Next
    INDEX
    Explanations

    references to statistical standards and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iou
    -0.44
    Rüyada
    -0.42
     renang
    -0.42
    tahui
    -0.42
    inghouse
    -0.41
    withIdentifier
    -0.40
     ģ
    -0.40
    μβρίου
    -0.40
     Hände
    -0.40
    ActionCreators
    -0.40
    POSITIVE LOGITS
    isation
    0.79
     deviation
    0.75
     Deviation
    0.67
    bred
    0.65
     bearer
    0.64
     Standard
    0.64
     deviations
    0.62
    Scaler
    0.61
    Deviation
    0.61
     Bearer
    0.60
    Activations Density 0.102%

    No Known Activations