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. 31-GEMMASCOPE-RES-16K
    6. 15996
    Prev
    Next
    INDEX
    Explanations

    keywords related to film festivals and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after punctuation or possessive apostrophe

    np_acts-logits-general · gemini-2.0-flash

    independent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.77
     olympiques
    -0.57
     autorytatywna
    -0.54
     Encyclopædia
    -0.51
    enciaga
    -0.50
    Personendaten
    -0.50
    getSystemService
    -0.50
     الرياضيه
    -0.49
     Enciclopedia
    -0.49
     ffilmiau
    -0.48
    POSITIVE LOGITS
     independent
    0.75
     independente
    0.68
     indipendente
    0.68
     independently
    0.67
     independiente
    0.64
    independent
    0.60
    獨立
    0.58
     Independent
    0.56
     независи
    0.56
     indépendante
    0.55
    Activations Density 0.218%

    No Known Activations