© 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. 34-GEMMASCOPE-RES-16K
    11. 16145
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and organizational efforts related to recycling

    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
    . 
    -1.16
     covid
    -1.05
     TikTok
    -1.05
    https
    -1.04
     COVID
    -1.02
     Covid
    -1.02
    ️
    -1.01
     
    -1.01
     onboarding
    -1.00
     🥲
    -1.00
    POSITIVE LOGITS
     idéia
    1.31
    faßt
    1.12
     muß
    1.11
     Daß
    1.10
     läßt
    1.02
     mußten
    0.98
     mußte
    0.94
     daß
    0.93
     Miß
    0.89
     biß
    0.88
    Activations Density 5.047%

    No Known Activations