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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 80227
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure in code

    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
    VIAF
    -0.51
     Wicidata
    -0.46
     Caus
    -0.45
    memor
    -0.45
    存于互联网档案馆
    -0.44
     grav
    -0.44
     виправивши
    -0.44
     mone
    -0.44
     Lut
    -0.43
     onStart
    -0.43
    POSITIVE LOGITS
    cinhas
    0.47
     végétale
    0.44
     AssemblyCulture
    0.43
     Vergine
    0.43
     Komunikasi
    0.41
     speranza
    0.41
     betrekking
    0.41
     grecque
    0.40
    retudo
    0.40
    errHandler
    0.40
    Activations Density 0.074%

    No Known Activations