© 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. 0-GEMMASCOPE-RES-16K
    11. 9459
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bab
    -0.53
    ib
    -0.53
    uro
    -0.52
     Bob
    -0.51
    bab
    -0.51
     Bag
    -0.50
    udo
    -0.50
     Band
    -0.49
    cy
    -0.49
    ache
    -0.49
    POSITIVE LOGITS
     when
    2.34
    when
    2.16
     cuando
    2.13
     quando
    2.08
     WHEN
    1.85
    cuando
    1.84
     kiedy
    1.84
     когда
    1.83
     wanneer
    1.80
     όταν
    1.74
    Activations Density 0.309%

    No Known Activations