© 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. 28-GEMMASCOPE-RES-16K
    11. 3418
    Prev
    Next
    INDEX
    Explanations

    details related to physiological disorders and statistical analyses of health metrics

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

    ending in "sistency", "ment", "tral", "ores", "stance", or "str"

    np_acts-logits-general · gemini-2.0-flash

    word endings and follow-ups

    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
     Савезне
    -0.72
    новниш
    -0.71
     ویکی‌پدی
    -0.68
    ंदीखरीदारी
    -0.68
    linawan
    -0.67
    SharedDtor
    -0.66
    alakip
    -0.66
    <unused52>
    -0.63
    <unused14>
    -0.62
    <pad>
    -0.61
    POSITIVE LOGITS
     iload
    0.42
    â
    0.38
    executeQuery
    0.37
     burberry
    0.33
     Europäischen
    0.33
    </b>
    0.32
     javafx
    0.32
    Ã
    0.30
    Muz
    0.30
    ************
    0.30
    Activations Density 2.720%

    No Known Activations