© 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. 9809
    Prev
    Next
    INDEX
    Explanations

    instances of low or no costs associated with a product or service

    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
    ⓧ
    -0.43
    errHandler
    -0.42
    setVerticalGroup
    -0.41
     pinulongan
    -0.39
     Мексичка
    -0.37
    pannt
    -0.35
     OFDb
    -0.35
    interopRequire
    -0.34
    ்ச
    -0.34
    writeFieldEnd
    -0.33
    POSITIVE LOGITS
     extra
    3.53
     additional
    3.20
    extra
    2.94
    additional
    2.89
     Extra
    2.72
     ekstra
    2.69
    Extra
    2.67
     EXTRA
    2.66
    Additional
    2.58
     Additional
    2.58
    Activations Density 1.353%

    No Known Activations