© 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. 28-GEMMASCOPE-RES-16K
    11. 3018
    Prev
    Next
    INDEX
    Explanations

    detailed and meaningful insights or understandings from complex information

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

    followed by prepositions like "of", "about", or "into"

    np_acts-logits-general · gemini-2.0-flash

    information about or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getProfile
    -0.34
    getProducts
    -0.34
    baomidou
    -0.32
     Stab
    -0.32
     torchvision
    -0.31
     legger
    -0.30
     Signature
    -0.30
     zit
    -0.30
    Stab
    -0.29
    successfully
    -0.29
    POSITIVE LOGITS
     about
    0.98
     tentang
    0.85
     mengenai
    0.81
     regarding
    0.80
    เกี่ยวกับ
    0.75
     concerning
    0.71
     siitä
    0.70
     acerca
    0.69
     Regarding
    0.69
     how
    0.69
    Activations Density 0.693%

    No Known Activations