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

    Neuronpedia

    Jacobian LensNEW
    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. 13566
    Prev
    Next
    INDEX
    Explanations

    references to meetings and their details

    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
     ModelExpression
    -0.65
     autorytatywna
    -0.51
    Hentet
    -0.50
    ScopeManager
    -0.47
     sztuki
    -0.47
    postsleuth
    -0.47
    ReusableCell
    -0.47
     okuyayım
    -0.47
     étoient
    -0.45
     jäl
    -0.45
    POSITIVE LOGITS
     meeting
    2.80
     meetings
    2.56
     Meeting
    2.33
    meeting
    2.31
    Meeting
    2.23
     Meetings
    2.13
     MEETING
    2.06
    meetings
    2.06
    Meetings
    1.98
     réunion
    1.66
    Activations Density 0.516%

    No Known Activations