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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5135
    Prev
    Next
    INDEX
    Explanations

    phrases related to artistic details and techniques in a specific context

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     or
    -0.28
     études
    -0.27
     workshops
    -0.25
     auster
    -0.25
    ·
    -0.25
     operational
    -0.24
     tournoi
    -0.24
    -
    -0.24
     brukar
    -0.24
     travaux
    -0.24
    POSITIVE LOGITS
    AndEndTag
    0.89
     disambiguazione
    0.85
     gynhyrchwyd
    0.82
     незавершена
    0.80
    windowFixed
    0.73
     AssemblyCulture
    0.73
    ConstraintMaker
    0.73
    Personensuche
    0.72
     betweenstory
    0.71
    richTextPanel
    0.71
    Activations Density 0.915%

    No Known Activations