© 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. 35-GEMMASCOPE-RES-16K
    11. 10873
    Prev
    Next
    INDEX
    Explanations

    elements related to visual or cinematic production techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.83
     vœux
    -0.76
     larmes
    -0.75
     âmes
    -0.74
     lèvres
    -0.73
     prêtres
    -0.72
     bienfaits
    -0.71
     dieux
    -0.66
     oiseaux
    -0.60
     rigue
    -0.60
    POSITIVE LOGITS
     setups
    1.27
     frameworks
    1.22
     environments
    1.20
     situations
    1.20
     programmes
    1.18
     programs
    1.18
     schemes
    1.18
     regimes
    1.16
     formats
    1.15
     regimens
    1.13
    Activations Density 6.084%

    No Known Activations