© 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. 20-GEMMASCOPE-RES-16K
    11. 811
    Prev
    Next
    INDEX
    Explanations

    elements related to teleportation and explosive effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    smoke, fire, and explosions

    np_acts-logits-general · gemini-2.0-flash

    smoke and visual effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.58
    JButton
    -0.57
    WebServlet
    -0.54
    InSection
    -0.53
    ostomy
    -0.52
    MockBean
    -0.50
     nahilalakip
    -0.49
     Normdatei
    -0.48
    BeginInit
    -0.48
    ContentAlignment
    -0.48
    POSITIVE LOGITS
     smoke
    1.30
     cloud
    1.06
     clouds
    1.04
     Smoke
    1.00
    smoke
    0.95
     smokes
    0.94
     nuage
    0.91
     plumes
    0.90
     vapour
    0.90
    Smoke
    0.89
    Activations Density 0.392%

    No Known Activations