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. 4-GEMMASCOPE-RES-16K
    6. 15880
    Prev
    Next
    INDEX
    Explanations

    terms and parameters related to lighting and color properties in graphical rendering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.78
    出版年
    -0.68
     يتيمه
    -0.63
     للمعارف
    -0.62
    zzleHttp
    -0.61
    Cyfeiriadau
    -0.60
    marginal
    -0.59
    Gambas
    -0.57
    kate
    -0.57
     resourceCulture
    -0.57
    POSITIVE LOGITS
    opacity
    0.83
     opacity
    0.66
    RGBA
    0.65
    withOpacity
    0.65
     quaternion
    0.62
    aternion
    0.60
    ARGB
    0.59
    argb
    0.59
    rgba
    0.56
    RGB
    0.49
    Activations Density 0.997%

    No Known Activations