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. 13037
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to organizational and administrative contexts

    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
    rsiniz
    -0.50
    énario
    -0.45
    Посилання
    -0.43
    AddHtmlAttribute
    -0.42
     gră
    -0.42
    pova
    -0.40
     przep
    -0.39
     mostaza
    -0.39
     tazas
    -0.39
     oświet
    -0.38
    POSITIVE LOGITS
    sidemargin
    0.45
    новништво
    0.43
     lees
    0.40
     referrerpolicy
    0.40
    Jeografia
    0.39
    fVar
    0.38
    facility
    0.38
    Hybrid
    0.37
    complexContent
    0.37
    杓
    0.37
    Activations Density 1.087%

    No Known Activations