Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15737
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle accidents and collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.60
     GetEnumerator
    -0.57
    +#+
    -0.57
    gnat
    -0.57
    ottes
    -0.55
    épaisseur
    -0.54
    indrical
    -0.53
     ouver
    -0.53
     spéciaux
    -0.52
    anjutan
    -0.52
    POSITIVE LOGITS
     accident
    0.88
     crash
    0.87
     crashed
    0.86
     crashes
    0.81
     wreck
    0.78
     collided
    0.77
     Accident
    0.75
     collision
    0.71
     wrecks
    0.71
     wrecked
    0.69
    Activations Density 0.142%

    No Known Activations