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. 3323
    Prev
    Next
    INDEX
    Explanations

    structural elements and metadata in technical documents

    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
     arşivlendi
    -0.44
    новниш
    -0.35
     eivät
    -0.30
    GraphicsUnit
    -0.30
     représ
    -0.30
    Clik
    -0.29
    stylers
    -0.29
     atracción
    -0.28
     wohin
    -0.27
     jí
    -0.27
    POSITIVE LOGITS
    endcsname
    0.80
     autorytatywna
    0.72
     nahilalakip
    0.69
    setVerticalGroup
    0.61
    SequentialGroup
    0.58
     OrderedDict
    0.57
    stateProvider
    0.56
     subsection
    0.56
    section
    0.56
     subsections
    0.55
    Activations Density 0.246%

    No Known Activations