© 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. 33-GEMMASCOPE-RES-16K
    11. 9390
    Prev
    Next
    INDEX
    Explanations

    devices and concepts related to electrostatics and insect traps

    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
     Trapp
    -0.40
     nyom
    -0.35
     retro
    -0.34
     Quarry
    -0.33
    pom
    -0.33
     sun
    -0.32
     aquarela
    -0.32
     gekomen
    -0.32
    encana
    -0.31
     Coen
    -0.31
    POSITIVE LOGITS
     electrical
    1.66
     Electrical
    1.55
     electric
    1.55
    Electrical
    1.52
    electrical
    1.47
     electricity
    1.45
     Electric
    1.43
    Electric
    1.40
     ELECTRIC
    1.40
    electric
    1.39
    Activations Density 1.176%

    No Known Activations