© 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. 18-GEMMASCOPE-RES-16K
    11. 6309
    Prev
    Next
    INDEX
    Explanations

    phrases related to fireworks and their display

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

    fireworks and explosions

    np_acts-logits-general · gemini-2.0-flash

    pyrotechnic fireworks formulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.80
    thâu
    -0.63
    kenstock
    -0.58
     occupé
    -0.55
     nursing
    -0.53
    Nursing
    -0.53
     bì
    -0.52
    ----</
    -0.52
    protoimpl
    -0.52
    водство
    -0.50
    POSITIVE LOGITS
     fireworks
    1.40
     explosion
    1.31
     deton
    1.30
     explode
    1.28
     firework
    1.27
     detonation
    1.26
     explosions
    1.26
     Fireworks
    1.25
     exploding
    1.20
     explosive
    1.19
    Activations Density 0.358%

    No Known Activations