© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6339
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft Office products and their associated file formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inscrivez
    -0.44
    GEBURTSDATUM
    -0.41
     Eigentum
    -0.36
     wykonania
    -0.34
    gefügt
    -0.33
     Abonnez
    -0.32
     păr
    -0.31
    expandindo
    -0.30
     pochod
    -0.30
     avulla
    -0.30
    POSITIVE LOGITS
    ulemon
    0.88
     Skyrim
    0.86
    TagMode
    0.81
     FIFA
    0.79
     QuickBooks
    0.78
     PUBG
    0.77
     Sonos
    0.77
    Fortnite
    0.75
    findpost
    0.75
     Beyoncé
    0.75
    Activations Density 3.810%

    No Known Activations