© 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. 36-GEMMASCOPE-RES-16K
    11. 7628
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.74
    parsedMessage
    -0.53
    lapsingToolbar
    -0.52
     '\\;'
    -0.52
    argout
    -0.51
     âmes
    -0.50
    IsContent
    -0.50
     FetchType
    -0.50
    OCCURRED
    -0.49
    fromnode
    -0.49
    POSITIVE LOGITS
    ings
    1.41
    INGS
    1.37
    tings
    1.21
     ings
    1.20
    ppings
    1.07
    nings
    1.05
    dings
    1.02
    NINGS
    1.02
    TINGS
    0.96
    settings
    0.94
    Activations Density 0.595%

    No Known Activations