© 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. 11-GEMMASCOPE-RES-16K
    11. 12584
    Prev
    Next
    INDEX
    Explanations

    references to search forms and filtering options in a web application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     living
    -0.47
     Bio
    -0.40
     td
    -0.40
     Img
    -0.40
     muscle
    -0.38
     Er
    -0.38
     nucle
    -0.38
     mus
    -0.38
     Lester
    -0.37
     Dore
    -0.37
    POSITIVE LOGITS
    addCriterion
    0.84
    IntoConstraints
    0.67
     resourceCulture
    0.59
    RenderAtEndOf
    0.58
    oredCriteria
    0.57
     sumpay
    0.54
    +#+#
    0.54
     desmotivaciones
    0.53
     tehd
    0.52
     çantası
    0.52
    Activations Density 0.266%

    No Known Activations