© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3143
    Prev
    Next
    INDEX
    Explanations

    references to car accidents and related injuries

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SpringBootTest
    -0.48
     gynhyrchwyd
    -0.42
    RTSC
    -0.42
    setVerticalGroup
    -0.40
    Composable
    -0.39
     antiviral
    -0.38
    UnusedPrivate
    -0.38
     المعيارى
    -0.36
    }]{
    -0.36
     invokingState
    -0.35
    POSITIVE LOGITS
     accident
    2.47
     accidents
    2.17
     Accident
    2.08
    accident
    2.05
     crash
    2.03
    Accident
    2.02
     ACCIDENT
    1.91
     Accidents
    1.85
     accidente
    1.78
     crashes
    1.72
    Activations Density 0.358%

    No Known Activations