© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4085
    Prev
    Next
    INDEX
    Explanations

    references to devices and their functionalities, particularly focusing on applications involving light and sound reduction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marquées
    -0.63
     dépasser
    -0.63
     prépar
    -0.62
     termica
    -0.61
     préparé
    -0.60
     apparaître
    -0.58
     campaigning
    -0.57
     réparation
    -0.56
     étudier
    -0.56
     priorité
    -0.55
    POSITIVE LOGITS
     absorb
    0.94
     absorbing
    0.87
     absorbs
    0.86
     trap
    0.79
     trapping
    0.75
     redirect
    0.74
     Absorb
    0.74
     prevent
    0.73
    absorb
    0.73
    extAlignment
    0.71
    Activations Density 0.784%

    No Known Activations