© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11939
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to blood tests and lab results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.97
    parsedMessage
    -0.89
    хьтан
    -0.85
    <unused43>
    -0.80
    <unused76>
    -0.80
    <unused42>
    -0.80
    <pad>
    -0.80
    <unused80>
    -0.79
    <unused74>
    -0.79
    <unused41>
    -0.79
    POSITIVE LOGITS
     ****
    0.40
    ..
    0.38
    ...
    0.35
    ****
    0.34
     fucking
    0.32
    !!!
    0.31
    !!
    0.30
    ?
    0.30
     ..
    0.29
    1
    0.29
    Activations Density 1.609%

    No Known Activations