© 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. 15-GEMMASCOPE-RES-16K
    6. 2939
    Prev
    Next
    INDEX
    Explanations

    structured data or metrics related to data visualization or charting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indicators of data or statistical summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.75
    expandindo
    -0.74
     vPvB
    -0.73
    Bioaccumulative
    -0.72
     autorytatywna
    -0.72
    
    -0.69
    indd
    -0.63
    تقاوى
    -0.62
    mappedBy
    -0.61
    NameInMap
    -0.58
    POSITIVE LOGITS
    RegressionTest
    0.57
     leksikon
    0.55
     Annotated
    0.53
     StatefulWidget
    0.45
     Alles
    0.42
    TabLayout
    0.41
    pence
    0.41
    arriver
    0.40
    ATN
    0.39
    .
    0.39
    Activations Density 0.858%

    No Known Activations