© 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. 22-GEMMASCOPE-RES-16K
    11. 5206
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administração
    -0.46
     Komunikasi
    -0.44
     hilos
    -0.44
     Investigación
    -0.43
     Relaciones
    -0.42
    SequentialGroup
    -0.41
     fiscales
    -0.41
     Mühe
    -0.40
     autón
    -0.40
     Lingkungan
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.58
     cheeky
    0.53
     softer
    0.53
    まあ
    0.53
    IndentedString
    0.52
     TextAppearance
    0.52
     Incidentally
    0.52
    FontOfSize
    0.51
    AnchorStyles
    0.51
     gauntlet
    0.51
    Activations Density 0.198%

    No Known Activations