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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2330
    Prev
    Next
    INDEX
    Explanations

    references to pixels in imaging contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.06
     AssemblyCulture
    -1.02
    DotNetBar
    -0.88
     Italijani
    -0.85
     kasarigan
    -0.82
    GOTREF
    -0.81
    Tembelea
    -0.80
     Wicidata
    -0.79
     propOrder
    -0.78
     învă
    -0.78
    POSITIVE LOGITS
    pol
    0.63
     pol
    0.63
    displayquote
    0.63
     Pol
    0.58
    mul
    0.57
    шту
    0.55
    clay
    0.55
     het
    0.55
    Pol
    0.54
    Mul
    0.53
    Activations Density 0.085%

    No Known Activations