© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2786
    Prev
    Next
    INDEX
    Explanations

    references to accidents and mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.86
    PerformLayout
    -0.83
     bershka
    -0.81
    TagMode
    -0.78
     declarat
    -0.77
     Shields
    -0.73
    rillation
    -0.72
    ิลปะ
    -0.71
    massen
    -0.71
    bereits
    -0.71
    POSITIVE LOGITS
     mistake
    1.12
     mistakes
    1.09
     Mistakes
    1.03
     accident
    0.99
     Mistake
    0.97
    Mistake
    0.92
     trick
    0.91
    Accident
    0.90
     Accident
    0.87
    accident
    0.86
    Activations Density 0.079%

    No Known Activations