© 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. 20-GEMMASCOPE-RES-16K
    11. 9032
    Prev
    Next
    INDEX
    Explanations

    situations involving collisions and accidents, particularly those involving vehicles

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

    associated with impact or accidents

    np_acts-logits-general · gemini-2.0-flash

    crashes and collisions

    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
    
    -0.68
     resourceCulture
    -0.62
     lenker
    -0.59
     Signalez
    -0.58
     GenerationType
    -0.58
     anhyd
    -0.56
     correctes
    -0.55
     تضيفلها
    -0.54
    urlencoded
    -0.53
    urati
    -0.53
    POSITIVE LOGITS
     collision
    1.42
     collide
    1.26
     colliding
    1.25
     crash
    1.23
     collided
    1.20
     collisions
    1.20
     Collision
    1.15
    collision
    1.10
     crashed
    1.09
     crashing
    1.05
    Activations Density 0.314%

    No Known Activations