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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10248
    Prev
    Next
    INDEX
    Explanations

    references to significant political events and figures in American history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.89
    BagConstraints
    -0.78
     Historical
    -0.78
    parsedMessage
    -0.77
    Historical
    -0.75
    tagHelperRunner
    -0.74
    Historic
    -0.74
     مشين
    -0.72
     HISTORICAL
    -0.71
     Historic
    -0.70
    POSITIVE LOGITS
     history
    1.05
    history
    0.64
     recorded
    0.62
     recent
    0.59
     истории
    0.54
     modern
    0.53
    recorded
    0.52
     geschiedenis
    0.51
     storia
    0.47
     história
    0.46
    Activations Density 0.313%

    No Known Activations