© 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. 27-GEMMASCOPE-RES-16K
    11. 10561
    Prev
    Next
    INDEX
    Explanations

    specific medical terminologies or concepts associated with cardiovascular health and related conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tation
    -0.60
     Comprometido
    -0.54
     utafitiHapana
    -0.53
    slidesToShow
    -0.53
    rawDesc
    -0.52
    complexContent
    -0.52
     mijne
    -0.51
    Jeografia
    -0.50
     zoude
    -0.50
     gezondheid
    -0.50
    POSITIVE LOGITS
    ी
    0.49
     Consig
    0.49
    y
    0.49
    SYS
    0.47
     Chio
    0.44
     McCon
    0.43
    <th>
    0.42
    𝖍
    0.42
    getActive
    0.42
     Sylvain
    0.41
    Activations Density 1.639%

    No Known Activations