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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8686
    Prev
    Next
    INDEX
    Explanations

    terms and parameters related to shading and lighting in graphics programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    jsonwebtoken
    -0.62
    sizeCache
    -0.61
    MockMvc
    -0.61
    AutoField
    -0.60
     Wikispecies
    -0.56
    mybatisplus
    -0.55
    LLocation
    -0.55
    PerformLayout
    -0.53
     HasFactory
    -0.52
    astify
    -0.50
    POSITIVE LOGITS
     texture
    0.87
     Texture
    0.77
     tex
    0.74
     TEXT
    0.72
     textures
    0.69
     тексту
    0.68
    texture
    0.68
     tekst
    0.67
     sampler
    0.67
    Texture
    0.65
    Activations Density 0.495%

    No Known Activations