© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6136
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle crashes and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     propOrder
    -0.71
    IntoConstraints
    -0.66
    出版年
    -0.62
     esternos
    -0.56
     FetchType
    -0.55
     Rada
    -0.55
    tagext
    -0.53
     CURIAM
    -0.52
    Tikang
    -0.52
    ьаж
    -0.50
    POSITIVE LOGITS
     crash
    1.87
     collision
    1.63
     Crash
    1.60
     crashed
    1.56
    crash
    1.51
    Crash
    1.46
     crashing
    1.45
     Collision
    1.45
     crashes
    1.42
    collision
    1.38
    Activations Density 0.153%

    No Known Activations