© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11408
    Prev
    Next
    INDEX
    Explanations

    phrases indicating urgency or conditions related to legal and medical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ública
    -0.51
    WebElementEntity
    -0.48
    addGap
    -0.48
    root
    -0.47
     השת
    -0.47
    Ort
    -0.45
     Strict
    -0.44
    sements
    -0.43
    migrationBuilder
    -0.43
     recevez
    -0.42
    POSITIVE LOGITS
     delay
    1.69
     delaying
    1.50
     procrastin
    1.50
     Delay
    1.47
     delayed
    1.43
     DELAY
    1.42
     delays
    1.37
     procrastination
    1.33
    Delay
    1.32
    delay
    1.31
    Activations Density 0.271%

    No Known Activations