© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13061
    Prev
    Next
    INDEX
    Explanations

    code related to light properties in 3D graphics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.43
    <eos>
    -0.40
    setProgress
    -0.36
    सं
    -0.35
    窮
    -0.35
     show
    -0.35
    upuesto
    -0.34
    i
    -0.34
     நி
    -0.34
    minWidth
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    1.14
    RectangleBorder
    0.95
    WriteTagHelper
    0.94
    MLLoader
    0.86
    GOTREF
    0.83
    setVerticalGroup
    0.83
    KommentareTeilen
    0.82
    \{\\
    0.81
     незавершена
    0.81
    IntoConstraints
    0.78
    Activations Density 0.548%

    No Known Activations