© 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. 9208
    Prev
    Next
    INDEX
    Explanations

    code structures and operations related to data sets and model handling in programming

    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
     nodeId
    -0.62
     getAge
    -0.59
     createTime
    -0.59
     groupId
    -0.58
     projectId
    -0.57
     deviceId
    -0.57
     userDao
    -0.56
     eventId
    -0.56
     orderId
    -0.56
     roomId
    -0.55
    POSITIVE LOGITS
     original
    0.86
     actual
    0.79
     target
    0.79
     previous
    0.77
    original
    0.74
     current
    0.74
     orig
    0.73
     Original
    0.73
    actual
    0.71
     prev
    0.70
    Activations Density 0.876%

    No Known Activations