© 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. 38-GEMMASCOPE-RES-16K
    11. 9895
    Prev
    Next
    INDEX
    Explanations

    terms related to warnings and safety protocols in operational instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    -0.43
    archiviato
    -0.38
    UserScript
    -0.38
     послу
    -0.35
    無料で
    -0.35
    šinou
    -0.34
    Население
    -0.33
    GeneratedMessage
    -0.33
     provision
    -0.33
     manageable
    -0.33
    POSITIVE LOGITS
     exposed
    0.98
     exposure
    0.97
     careless
    0.93
     accidentally
    0.93
     unprotected
    0.89
     improperly
    0.88
    exposed
    0.88
     Exposure
    0.85
    exposure
    0.85
    Exposure
    0.85
    Activations Density 0.696%

    No Known Activations