© 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. 12919
    Prev
    Next
    INDEX
    Explanations

    content related to contests, prizes, and incentives

    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
    DOCTYPE
    -0.38
    elemField
    -0.37
     awakeFromNib
    -0.34
    basicConfig
    -0.33
     cita
    -0.33
    InitVars
    -0.33
    AddHtmlAttribute
    -0.33
     citas
    -0.31
    ghum
    -0.31
    Viitteet
    -0.31
    POSITIVE LOGITS
     prizes
    1.88
     prize
    1.87
     Prizes
    1.60
     Prize
    1.54
    prize
    1.54
    Prize
    1.52
    Prizes
    1.49
     PRIZE
    1.47
     contest
    1.41
     raffle
    1.41
    Activations Density 0.131%

    No Known Activations