© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11355
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "coming."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.50
     Urteil
    -0.37
    yPos
    -0.33
    pakking
    -0.32
     poi
    -0.32
    手帳
    -0.32
    NSURL
    -0.31
     puro
    -0.30
    AlterField
    -0.30
     tuple
    -0.30
    POSITIVE LOGITS
     coming
    3.59
    Coming
    3.38
     Coming
    3.33
    coming
    3.16
     COMING
    3.08
    COMING
    2.58
     comming
    2.05
     incoming
    1.82
     comin
    1.78
     forthcoming
    1.67
    Activations Density 0.096%

    No Known Activations