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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 779
    Prev
    Next
    INDEX
    Explanations

    color-related properties and configurations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.55
    tocin
    -0.55
    Manbalar
    -0.53
    ConstraintMaker
    -0.47
    errHandler
    -0.46
    RectangleBorder
    -0.46
     sympy
    -0.45
    verifyException
    -0.43
    makeConstraints
    -0.42
    paksa
    -0.42
    POSITIVE LOGITS
     RGB
    0.76
     lightness
    0.75
     transparency
    0.74
    rrggbb
    0.74
     saturation
    0.73
    transparency
    0.72
     hue
    0.71
    RGB
    0.70
     Saturation
    0.70
     channel
    0.70
    Activations Density 0.170%

    No Known Activations