© 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. 15-GEMMASCOPE-RES-16K
    11. 1847
    Prev
    Next
    INDEX
    Explanations

    references to action and consequences in high-stakes scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     velkommen
    -0.36
     Dominant
    -0.34
    ніципалі
    -0.32
     Patches
    -0.32
     Processing
    -0.32
    Patches
    -0.31
    httphttps
    -0.31
     sẻ
    -0.31
    centa
    -0.31
    icorn
    -0.30
    POSITIVE LOGITS
    DockStyle
    0.61
     EMERGENCY
    0.55
     emergency
    0.54
    emergency
    0.54
    asztok
    0.52
    Emergency
    0.52
    trigger
    0.51
     triggered
    0.50
     trigger
    0.48
     invoke
    0.47
    Activations Density 1.078%

    No Known Activations