© 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. 20-GEMMASCOPE-RES-16K
    11. 13261
    Prev
    Next
    INDEX
    Explanations

    references to events and their scheduling details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.48
    UnsafeEnabled
    -0.43
     utafitiHapana
    -0.41
    arraycopy
    -0.36
    Diwedd
    -0.34
    oredCriteria
    -0.33
     Италијани
    -0.32
     swamp
    -0.32
     olig
    -0.32
     pourriez
    -0.32
    POSITIVE LOGITS
     edition
    0.71
     årets
    0.58
     édition
    0.57
     verteilt
    0.54
     editions
    0.52
     път
    0.51
    edition
    0.51
     Ausgabe
    0.50
     Edition
    0.50
     iteration
    0.49
    Activations Density 0.161%

    No Known Activations