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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10434
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to nuclear energy, weapons, and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.81
     Emin
    -0.75
     CreateTagHelper
    -0.72
     Viceroy
    -0.70
     تضيفلها
    -0.70
     Roskov
    -0.69
    knapp
    -0.66
     CommonModule
    -0.65
    ilanth
    -0.65
     Phari
    -0.64
    POSITIVE LOGITS
     nuclear
    3.23
     Nuclear
    2.91
    nuclear
    2.86
    Nuclear
    2.79
     NUCLEAR
    2.60
     nucléaire
    2.26
    uclear
    2.03
     nukes
    1.82
     ядер
    1.82
    NUC
    1.72
    Activations Density 0.109%

    No Known Activations