© 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. 24-GEMMASCOPE-RES-16K
    6. 153
    Prev
    Next
    INDEX
    Explanations

    information related to patient profiles and updates in healthcare systems

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

    Data correction/access requests

    np_acts-logits-general · gemini-2.0-flash

    data accuracy and inaccuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الدراسه
    -0.43
    rodow
    -0.35
     thử
    -0.35
     createSlice
    -0.33
     Վերցված
    -0.30
     Lokales
    -0.29
     experiment
    -0.28
    webElementGuid
    -0.28
     чек
    -0.27
    govina
    -0.27
    POSITIVE LOGITS
     inaccuracies
    0.82
     accuracy
    0.80
     inaccurate
    0.76
     updating
    0.71
     Updating
    0.71
    Accurate
    0.71
     information
    0.71
     accurate
    0.70
     Accuracy
    0.70
     inaccuracy
    0.69
    Activations Density 0.341%

    No Known Activations