© 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. 7238
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and references to cycles or recurring events

    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
    once
    -0.84
    Once
    -0.82
     Once
    -0.73
     once
    -0.72
    ONCE
    -0.69
     ONCE
    -0.68
    一旦
    -0.42
     masih
    -0.42
     finalmente
    -0.40
     ModelExpression
    -0.40
    POSITIVE LOGITS
     ag
    1.30
     gain
    1.05
     agen
    1.00
     again
    0.95
     Ag
    0.95
    gain
    0.94
    agin
    0.93
    Ag
    0.91
     aga
    0.88
     AG
    0.85
    Activations Density 0.146%

    No Known Activations