© 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. 14-GEMMASCOPE-RES-16K
    11. 5489
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kirchen
    -0.44
     Gebir
    -0.42
     jurisdic
    -0.41
     volantes
    -0.40
     courant
    -0.40
     vaste
    -0.40
     Dunlap
    -0.40
    sieurs
    -0.40
     ministère
    -0.40
     resources
    -0.39
    POSITIVE LOGITS
    Be
    0.70
    ToBe
    0.69
    fromnode
    0.68
     Be
    0.67
    LookAnd
    0.67
     be
    0.64
    postIndex
    0.62
     propOrder
    0.58
     быть
    0.57
    toBe
    0.56
    Activations Density 0.151%

    No Known Activations