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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 5771
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests for additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    calls-to-action directing readers to external resources for more information.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.38
    sizeCache
    -0.33
    بوابة
    -0.31
     afbeeldingen
    -0.29
     við
    -0.28
     daar
    -0.28
     चीज़ों
    -0.28
    GenerationType
    -0.28
     pourriez
    -0.27
     mať
    -0.27
    POSITIVE LOGITS
     visit
    2.25
     Visit
    1.84
    visit
    1.84
     visited
    1.72
     VISIT
    1.70
     visits
    1.61
    Visit
    1.60
     visita
    1.55
     visiting
    1.54
     visite
    1.48
    Activations Density 0.164%

    No Known Activations