© 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. 3-GEMMASCOPE-RES-16K
    11. 9536
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "ce" (meaning "this" in French)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gonic
    -0.60
    RenderAtEndOf
    -0.60
    GEBURTSDATUM
    -0.59
    GTCX
    -0.58
    providedIn
    -0.57
    msgTypes
    -0.51
    parsedMessage
    -0.50
    ::_('
    -0.49
    exitRule
    -0.49
    ",@"
    -0.48
    POSITIVE LOGITS
     this
    1.15
     these
    1.10
     This
    1.03
    This
    1.02
     acest
    1.00
     này
    0.97
     These
    0.96
     THIS
    0.95
     diesen
    0.94
     THESE
    0.94
    Activations Density 1.001%

    No Known Activations