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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9861
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to image processing and color conversions

    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
    tocin
    -0.65
    RectangleBorder
    -0.64
    ConstraintMaker
    -0.48
    ValueGeneration
    -0.45
     sympy
    -0.44
    rshire
    -0.44
     ***!
    -0.43
     DialogInterface
    -0.42
     batteria
    -0.41
    unnitel
    -0.40
    POSITIVE LOGITS
     RGB
    0.95
    RGB
    0.86
    aarrggbb
    0.84
     color
    0.84
     colour
    0.82
     rgb
    0.77
    rrggbb
    0.76
    rgb
    0.75
     channels
    0.75
     channel
    0.75
    Activations Density 0.219%

    No Known Activations