© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14717
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eivät
    -0.63
     honneur
    -0.60
     kanssa
    -0.60
     poszczegól
    -0.57
     Wohnungen
    -0.56
     autorité
    -0.54
     intenção
    -0.52
     niitä
    -0.52
     policías
    -0.52
     dimaksud
    -0.52
    POSITIVE LOGITS
    ⤹
    0.71
     surla
    0.65
     Савезне
    0.65
    >\<^
    0.63
     joint
    0.63
    setof
    0.61
     мәкал
    0.61
    quelize
    0.61
     a
    0.60
    ronpa
    0.59
    Activations Density 0.587%

    No Known Activations