© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13090
    Prev
    Next
    INDEX
    Explanations

    references to LED technology and related components

    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
    슷
    -0.59
    lands
    -0.58
    saraba
    -0.57
     dilan
    -0.56
     lick
    -0.55
     GUST
    -0.54
     way
    -0.53
     Bhu
    -0.53
    onActivityResult
    -0.52
     δικ
    -0.52
    POSITIVE LOGITS
     LED
    2.10
     LEDs
    1.78
    LED
    1.72
     leds
    1.19
     OLED
    0.96
    leds
    0.93
     Diode
    0.93
    диод
    0.93
    VersionUID
    0.90
     diode
    0.88
    Activations Density 0.114%

    No Known Activations