© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10541
    Prev
    Next
    INDEX
    Explanations

    instances of the word "an" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étoit
    -0.67
    attendre
    -0.60
    assemblée
    -0.58
    égard
    -0.57
    occupe
    -0.57
    épaisseur
    -0.56
    extré
    -0.56
     folio
    -0.55
    vidéo
    -0.55
    occuper
    -0.54
    POSITIVE LOGITS
     assortment
    0.73
     array
    0.72
     entire
    0.72
     example
    0.68
     excellent
    0.68
     important
    0.66
     enormous
    0.66
     actual
    0.66
     impressive
    0.66
     absolute
    0.65
    Activations Density 0.276%

    No Known Activations