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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80877
    Prev
    Next
    INDEX
    Explanations

    aspects related to socio-economic factors, particularly those influencing health and development

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

    may contribute, has led

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     BoxDecoration
    -0.57
     EconPapers
    -0.56
     StatelessWidget
    -0.53
     lateinit
    -0.52
    styleUrls
    -0.51
    EndInit
    -0.50
     nhàng
    -0.50
    criminator
    -0.50
     discriminator
    -0.49
     galle
    -0.48
    POSITIVE LOGITS
     ویکی‌پدی
    0.50
     Aufwand
    0.48
     creciente
    0.46
     Verhält
    0.44
     creciendo
    0.43
     venganza
    0.42
     crece
    0.41
     oscuridad
    0.41
     expansión
    0.41
     alfombra
    0.40
    Activations Density 0.028%

    No Known Activations