© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9050
    Prev
    Next
    INDEX
    Explanations

    terms related to danger and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrer
    -0.40
    itzende
    -0.38
     virgen
    -0.37
     BytesLike
    -0.36
     sanitized
    -0.36
     táctil
    -0.35
     rígida
    -0.34
     cœurs
    -0.33
    nezeu
    -0.32
     âmes
    -0.32
    POSITIVE LOGITS
     danger
    1.84
     Danger
    1.75
    danger
    1.70
    Danger
    1.70
     dangerous
    1.64
     dangers
    1.56
     Dangerous
    1.50
    dangerous
    1.49
     threat
    1.47
     peligro
    1.43
    Activations Density 0.226%

    No Known Activations