© 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. 35-GEMMASCOPE-RES-16K
    11. 14928
    Prev
    Next
    INDEX
    Explanations

    phrases related to inventions and their historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.68
    rungsseite
    -0.68
     nahilalakip
    -0.64
    tagHelperRunner
    -0.60
    httphttps
    -0.57
    Sklici
    -0.54
     muebles
    -0.53
     Symptome
    -0.52
     zaś
    -0.52
     Jugendlichen
    -0.52
    POSITIVE LOGITS
    styleType
    0.41
     tra
    0.40
     ze
    0.38
     anti
    0.38
     sou
    0.37
     cro
    0.37
     bon
    0.36
     ap
    0.36
     tro
    0.36
     fre
    0.35
    Activations Density 1.037%

    No Known Activations