© 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. 5-GEMMASCOPE-RES-16K
    11. 7027
    Prev
    Next
    INDEX
    Explanations

    terms related to danger or harmfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.80
     برانيه
    -0.77
     Drittel
    -0.77
    ClientSize
    -0.77
     ulang
    -0.72
    harusnya
    -0.72
    hidupan
    -0.72
    ksesta
    -0.71
     ansatte
    -0.70
    ressee
    -0.70
    POSITIVE LOGITS
     danger
    1.88
     Danger
    1.79
     dangers
    1.69
     dangerous
    1.66
    danger
    1.66
    Danger
    1.64
     Dangers
    1.54
     Dangerous
    1.53
    Dangerous
    1.49
    dangerous
    1.49
    Activations Density 0.055%

    No Known Activations