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. 5-GEMMASCOPE-RES-16K
    6. 10499
    Prev
    Next
    INDEX
    Explanations

    terms related to image processing and color space conversions, particularly in the context of the HSV color model

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.69
     للاسماء
    -0.69
    AddRange
    -0.55
    chauff
    -0.54
    baño
    -0.54
    MemoryWarning
    -0.52
     дописавши
    -0.52
    ganta
    -0.50
    CloseOperation
    -0.49
    rungsseite
    -0.49
    POSITIVE LOGITS
    opencv
    0.58
     TextAppearance
    0.53
     isNameExpr
    0.52
    TagHelper
    0.51
    Joy
    0.51
    ReferenceEquals
    0.50
     Anam
    0.50
     weighted
    0.49
    SerializedName
    0.48
     housewives
    0.48
    Activations Density 1.191%

    No Known Activations