© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and data related to biomedical research and health metrics

    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
    AddTagHelper
    -0.65
    CppMethod
    -0.63
     lenker
    -0.42
    ftagPool
    -0.40
     esternos
    -0.38
    rétaire
    -0.36
     '\\;'
    -0.35
     HasFactory
    -0.35
    GraphicsUnit
    -0.34
    ViewFeatures
    -0.33
    POSITIVE LOGITS
     greater
    1.95
     less
    1.91
    greater
    1.70
     exceeding
    1.65
     below
    1.64
     ≥
    1.63
     above
    1.59
    小于
    1.58
     Less
    1.56
     ≤
    1.55
    Activations Density 4.221%

    No Known Activations