© 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. 33-GEMMASCOPE-RES-16K
    11. 13529
    Prev
    Next
    INDEX
    Explanations

    announcements and details about events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     milliard
    -0.47
    sendLogPayload
    -0.45
     dodgy
    -0.38
     בישראל
    -0.38
     banal
    -0.37
    assertRaises
    -0.36
     AllMusic
    -0.35
     criticised
    -0.34
    Grüsse
    -0.34
     BadRequest
    -0.34
    POSITIVE LOGITS
     graciously
    0.74
     volunteers
    0.74
    WebElementEntity
    0.72
     fundraiser
    0.71
     sponsoring
    0.69
     Donations
    0.69
     voluntarios
    0.69
     volunteer
    0.68
     refreshments
    0.68
     donations
    0.67
    Activations Density 0.334%

    No Known Activations