© 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. 17-GEMMASCOPE-RES-16K
    11. 802
    Prev
    Next
    INDEX
    Explanations

    words related to potential conditions or uncertainties in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extérieurs
    -0.66
     élevés
    -0.55
     extérieures
    -0.54
     hauts
    -0.53
     blessés
    -0.52
     vélos
    -0.51
    miljø
    -0.50
     økonom
    -0.50
     laag
    -0.50
     rifer
    -0.49
    POSITIVE LOGITS
     downright
    1.02
     outright
    0.89
     actual
    0.78
     actually
    0.77
    actually
    0.69
    RenderAtEndOf
    0.68
    actual
    0.66
    期刊论文
    0.64
    Actually
    0.60
     كومونز
    0.59
    Activations Density 0.248%

    No Known Activations