© 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. 11-GEMMASCOPE-RES-16K
    11. 6537
    Prev
    Next
    INDEX
    Explanations

    phrases related to crime and safety incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.65
     Italijanski
    -0.63
    paksa
    -0.61
     AssemblyCulture
    -0.60
    basicConfig
    -0.53
    CROSSTALK
    -0.53
     autorytatywna
    -0.51
    Referencies
    -0.51
    новништво
    -0.50
     StatefulWidget
    -0.49
    POSITIVE LOGITS
     incidents
    0.98
     accidents
    0.89
     accidentes
    0.80
     cases
    0.80
     deaths
    0.77
     instances
    0.76
     incident
    0.74
     happened
    0.74
     injuries
    0.72
     Incidents
    0.72
    Activations Density 0.607%

    No Known Activations