© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15835
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety incidents and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.71
     AssemblyCulture
    -0.62
    WithIOException
    -0.51
    INSEE
    -0.50
     Constitucional
    -0.50
     adel
    -0.49
     atof
    -0.49
    ichthys
    -0.47
    angebot
    -0.47
     تضيفلها
    -0.46
    POSITIVE LOGITS
     accidents
    0.73
     incidents
    0.72
     occurrences
    0.70
     incidence
    0.68
     occ
    0.65
     fatal
    0.63
     fatalities
    0.63
     accidentes
    0.62
     occurrence
    0.62
     occurred
    0.61
    Activations Density 0.087%

    No Known Activations