© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5286
    Prev
    Next
    INDEX
    Explanations

    variations of the word "be" in multiple forms

    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
     GenerationType
    -0.48
     Krankheiten
    -0.42
     achtergrond
    -0.42
     Савезне
    -0.42
    DIPSETTING
    -0.42
     vroe
    -0.41
    toarele
    -0.41
     Rücksicht
    -0.41
     Zustimmung
    -0.40
    digde
    -0.40
    POSITIVE LOGITS
     BE
    2.13
    BE
    1.98
     Be
    1.97
    Be
    1.90
    be
    1.84
     Bé
    1.78
     bea
    1.78
     бе
    1.77
     Bea
    1.75
    Bea
    1.74
    Activations Density 0.891%

    No Known Activations