© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1390
    Prev
    Next
    INDEX
    Explanations

    phrases indicating interest or participation in activities or subjects

    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
    ---+
    -0.52
     honte
    -0.49
    Portale
    -0.48
     createSprite
    -0.48
     Evidence
    -0.46
    ůvod
    -0.46
    NewReader
    -0.46
    mittances
    -0.46
     LUMP
    -0.46
    IBU
    -0.45
    POSITIVE LOGITS
     interest
    3.23
    interest
    2.84
     Interest
    2.72
     INTEREST
    2.69
    Interest
    2.62
     interests
    2.54
    INTEREST
    2.45
     interested
    2.44
     interés
    2.21
     interes
    2.20
    Activations Density 0.445%

    No Known Activations