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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10214
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to observation and surveillance

    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
    isinstance
    -0.29
    有着
    -0.28
    The
    -0.28
     versions
    -0.28
    They
    -0.27
    respectively
    -0.27
    它们
    -0.26
    These
    -0.26
     respectivamente
    -0.25
    genossen
    -0.25
    POSITIVE LOGITS
     propOrder
    1.13
     largest
    1.05
     entire
    1.03
     same
    1.00
     biggest
    0.97
     slightest
    0.93
     remainder
    0.92
     smallest
    0.92
     own
    0.91
     youngest
    0.91
    Activations Density 1.822%

    No Known Activations