© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    references to legal texts and manuals related to immigration and mental health disorders

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

    Ordinal numbers followed by "ed", or "edition"

    np_acts-logits-general · gemini-2.0-flash

    book edition numbers

    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
     noDo
    -0.42
    bkz
    -0.40
     Infórmanos
    -0.39
    SourceChecksum
    -0.38
    CodeAnalysis
    -0.38
     naselje
    -0.37
     torchvision
    -0.37
    expandindo
    -0.34
    deuse
    -0.33
    NSNumber
    -0.33
    POSITIVE LOGITS
     edition
    1.24
     Edition
    1.03
    edition
    1.02
     revised
    1.01
     fifth
    1.00
     fourth
    1.00
     second
    1.00
     third
    0.98
    Edition
    0.98
     édition
    0.96
    Activations Density 0.306%

    No Known Activations