© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    government and organizational announcements or updates

    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
    現在は
    -0.96
    今は
    -0.93
     dabar
    -0.92
     nyní
    -0.90
     subsequent
    -0.90
    今後も
    -0.89
     aujourd
    -0.89
     actuellement
    -0.89
    最近は
    -0.88
     później
    -0.88
    POSITIVE LOGITS
     suddenly
    0.74
     announced
    0.70
    suddenly
    0.70
     finally
    0.66
     officially
    0.65
     announce
    0.63
     вдруг
    0.60
    突然
    0.60
     abruptly
    0.58
    EDEFAULT
    0.57
    Activations Density 0.386%

    No Known Activations