Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2811
    Prev
    Next
    INDEX
    Explanations

    references to various fields of study or disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angeran
    -0.52
    äter
    -0.44
     Alvarado
    -0.42
    illium
    -0.41
    thinkable
    -0.40
     acero
    -0.40
     geng
    -0.39
     Coolidge
    -0.39
    menos
    -0.39
     frem
    -0.38
    POSITIVE LOGITS
     sector
    0.99
     settore
    0.94
     industry
    0.92
     sectors
    0.92
    SpringBootTest
    0.84
     professions
    0.83
    industry
    0.80
     secteurs
    0.78
     industries
    0.78
     setor
    0.78
    Activations Density 0.377%

    No Known Activations