© 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. 24-GEMMASCOPE-RES-16K
    11. 5609
    Prev
    Next
    INDEX
    Explanations

    terms associated with time measurements and occurrences

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

    ending in "-ly", "-nt", "-age", or "-ar"

    np_acts-logits-general · gemini-2.0-flash

    adverbs and quantifiers

    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
     nahilalakip
    -0.42
     autorytatywna
    -0.41
    UrlResolution
    -0.41
    évaluateur
    -0.38
    writerow
    -0.35
    Pautan
    -0.35
     surla
    -0.34
     Schwert
    -0.33
    verwijspagina
    -0.32
    phòng
    -0.32
    POSITIVE LOGITS
    MemoryWarning
    0.63
     Italijani
    0.55
    arrhea
    0.52
    abetes
    0.52
    RegistryLite
    0.51
     Italijanski
    0.50
     wholesale
    0.50
     jScrollPane
    0.50
    ichio
    0.49
     postIndex
    0.48
    Activations Density 0.687%

    No Known Activations