© 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. 30-GEMMASCOPE-RES-16K
    11. 12416
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online resources

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

    Followed by letters

    np_acts-logits-general · gemini-2.0-flash

    scanning documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.44
     Lord
    -0.41
     lord
    -0.40
     makeStyles
    -0.38
    派
    -0.36
     mandarin
    -0.36
     Вікіпе
    -0.35
    ❯
    -0.35
     voc
    -0.34
    orcid
    -0.34
    POSITIVE LOGITS
     digitized
    0.75
     scanned
    0.68
     scans
    0.66
     JSTOR
    0.59
     scanning
    0.56
     scan
    0.54
    scanning
    0.54
    ChildScrollView
    0.53
     Scanning
    0.52
    Scanning
    0.50
    Activations Density 0.342%

    No Known Activations