© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    references to specific topics or categories, particularly relating to technology, gaming, and community forums

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

    Word associations with categories or types

    np_acts-logits-general · gemini-2.0-flash

    domains and categories

    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
    parsedMessage
    -0.82
    новништво
    -0.76
    GEBURTSDATUM
    -0.70
    ьаж
    -0.67
    StructEnd
    -0.66
    RTHOOK
    -0.63
    MethodManager
    -0.61
    Билгалдахарш
    -0.61
    FontOfSize
    -0.57
     AssemblyVersion
    -0.57
    POSITIVE LOGITS
     category
    0.82
     genre
    0.77
     sector
    0.69
     region
    0.67
     realm
    0.66
     industry
    0.60
     format
    0.57
     area
    0.57
     domain
    0.56
     categoria
    0.55
    Activations Density 0.778%

    No Known Activations