© 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. 6-GEMMASCOPE-RES-16K
    11. 13700
    Prev
    Next
    INDEX
    Explanations

    the concept of danger and threats to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toString
    -0.54
     CommonModule
    -0.50
    فية
    -0.47
    ملة
    -0.46
    出版年
    -0.46
    雀
    -0.45
     Kälte
    -0.45
    cheon
    -0.44
    riedenheit
    -0.43
     tears
    -0.43
    POSITIVE LOGITS
     dangerous
    1.52
     unsafe
    1.52
     safer
    1.46
     danger
    1.42
    safety
    1.39
     safety
    1.39
    dangerous
    1.38
     peligroso
    1.37
     safest
    1.34
     pelig
    1.32
    Activations Density 0.283%

    No Known Activations