© 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. 11403
    Prev
    Next
    INDEX
    Explanations

    terms related to the disposal of nuclear waste and its safety implications

    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
     jembatan
    -0.43
    обще
    -0.42
    $_['
    -0.42
     goma
    -0.39
    __*/
    -0.39
     rubber
    -0.39
    __.__
    -0.38
    kong
    -0.38
    LPG
    -0.38
    rž
    -0.38
    POSITIVE LOGITS
     nuclear
    1.33
     radioactive
    1.28
     Nuclear
    1.20
     nucléaire
    1.18
     Radioactive
    1.16
    Nuclear
    1.15
    nuclear
    1.13
     radioactivity
    1.10
     nuclé
    1.07
     radionuc
    1.06
    Activations Density 0.468%

    No Known Activations