Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51993
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wapV
    -0.46
     целе
    -0.35
     लग
    -0.34
    IConfiguration
    -0.33
     Lun
    -0.33
     מר
    -0.33
     hos
    -0.32
    방
    -0.32
    Lato
    -0.31
     مض
    -0.31
    POSITIVE LOGITS
     nonUne
    0.60
    RenderAtEndOf
    0.57
     Administrativna
    0.53
     eventual
    0.52
    MADRID
    0.50
     Numerade
    0.50
     nahilalakip
    0.50
    こうして
    0.48
    WithIOException
    0.48
     autorytatywna
    0.48
    Activations Density 0.023%

    No Known Activations