© 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. 10128
    Prev
    Next
    INDEX
    Explanations

    instances of hiding or concealed elements

    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
     jurk
    -0.57
    PhysRev
    -0.56
    WindowConstants
    -0.54
    +#+
    -0.52
    ActionPerformed
    -0.50
    VolleyError
    -0.48
    relationship
    -0.48
     prestations
    -0.47
     eventType
    -0.47
    prefixer
    -0.47
    POSITIVE LOGITS
     hidden
    1.19
     hiding
    1.05
     Hidden
    1.05
     hide
    1.01
     verborgen
    0.97
    Hidden
    0.95
    hidden
    0.94
     concealed
    0.93
     concealing
    0.93
     secret
    0.91
    Activations Density 0.155%

    No Known Activations