© 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. 10397
    Prev
    Next
    INDEX
    Explanations

    terms related to crashes and explosions

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

    car crashes or market crashes

    np_acts-logits-general · gemini-2.0-flash

    crash and explosions

    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
    muo
    -0.52
     slip
    -0.50
    gyz
    -0.50
    יו
    -0.48
    Subjects
    -0.48
     fing
    -0.48
     rette
    -0.48
     kelle
    -0.47
    ifera
    -0.47
     chameleon
    -0.47
    POSITIVE LOGITS
     Crash
    0.95
     crash
    0.92
     explosions
    0.92
     crashes
    0.88
     crashed
    0.87
     Cras
    0.85
    💥
    0.82
     wrecks
    0.82
    Crash
    0.82
    oredCriteria
    0.81
    Activations Density 0.197%

    No Known Activations