© 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. 3-GEMMASCOPE-RES-16K
    11. 7153
    Prev
    Next
    INDEX
    Explanations

    references to danger in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.74
     gynhyrchwyd
    -0.72
    setVerticalGroup
    -0.70
     مرئيه
    -0.67
     <=",
    -0.67
    harusnya
    -0.66
     ulang
    -0.65
    ClientSize
    -0.65
     Lup
    -0.65
     برانيه
    -0.64
    POSITIVE LOGITS
     danger
    3.12
     Danger
    2.85
     dangers
    2.67
    Danger
    2.61
    danger
    2.60
     dangerous
    2.44
     Dangers
    2.33
    dangerous
    2.17
     Dangerous
    2.13
    Dangerous
    2.07
    Activations Density 0.041%

    No Known Activations