© 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. 2-GEMMASCOPE-RES-16K
    11. 13191
    Prev
    Next
    INDEX
    Explanations

    phrases that involve expressions of speaking or stating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.48
    astéroïdes
    -0.45
    المناصب
    -0.38
     ence
    -0.36
     depositphotos
    -0.34
     reaſon
    -0.34
     quæ
    -0.34
     talk
    -0.34
     reafon
    -0.33
    noons
    -0.33
    POSITIVE LOGITS
     stating
    1.87
     saying
    1.69
     indicating
    1.63
     pointing
    1.60
     explaining
    1.54
     suggesting
    1.52
     noting
    1.50
     describing
    1.48
    saying
    1.46
     telling
    1.44
    Activations Density 0.377%

    No Known Activations