© 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. 22-GEMMASCOPE-RES-16K
    11. 9513
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of tools or instruments, particularly in technical or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.76
     démocr
    -0.72
     fidé
    -0.71
     ennemi
    -0.68
     vôtre
    -0.67
     bénéficiaire
    -0.63
     vœ
    -0.61
     feroit
    -0.59
     répon
    -0.59
     Connectez
    -0.58
    POSITIVE LOGITS
    riezmann
    0.66
     lenker
    0.61
     bParam
    0.58
     LeBlanc
    0.56
     Bourgoin
    0.55
    avoie
    0.54
    authier
    0.52
     Citron
    0.52
    ondre
    0.52
    ladel
    0.51
    Activations Density 0.813%

    No Known Activations