© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 14159
    Prev
    Next
    INDEX
    Explanations

    tense expressions involving conflict or tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.53
    AccessorTable
    -0.51
     disambiguazione
    -0.50
     BytesLike
    -0.47
    Архівовано
    -0.47
     للمعارف
    -0.47
     film
    -0.47
    addCriterion
    -0.46
    Bakgrunnsstoff
    -0.46
    構
    -0.46
    POSITIVE LOGITS
     season
    0.63
    season
    0.57
     säs
    0.55
     Season
    0.55
    Season
    0.52
     stagione
    0.51
     sezon
    0.50
    シーズン
    0.50
     الموسم
    0.50
     SEASON
    0.48
    Activations Density 0.187%

    No Known Activations