© 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. 34-GEMMASCOPE-RES-16K
    11. 9638
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     séjours
    -0.45
     stance
    -0.38
     boî
    -0.37
     enfans
    -0.36
    forName
    -0.35
    Overview
    -0.34
    ModelMap
    -0.34
     écrans
    -0.34
    OCCURRED
    -0.34
     poches
    -0.33
    POSITIVE LOGITS
     beiden
    0.76
     dignité
    0.70
     meisten
    0.67
     démocratie
    0.66
     demás
    0.65
     două
    0.63
    demás
    0.63
     compétence
    0.62
     meeste
    0.60
     fleste
    0.60
    Activations Density 0.040%

    No Known Activations