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. 12591
    Prev
    Next
    INDEX
    Explanations

    references to discounts and promotions related to products

    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
    à
    -0.42
    ë
    -0.41
    ว่า
    -0.38
    >>
    -0.38
    往
    -0.36
     unha
    -0.35
    erp
    -0.35
    名
    -0.35
    IF
    -0.35
    __(
    -0.34
    POSITIVE LOGITS
     autorytatywna
    1.11
    Autoritní
    1.05
    URLException
    1.00
    __*/
    0.98
    ArrowToggle
    0.94
    setVerticalGroup
    0.92
    complexContent
    0.92
     ModelExpression
    0.90
     internetowa
    0.89
     ویکی‌پدی
    0.87
    Activations Density 0.099%

    No Known Activations