© 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. 12-GEMMASCOPE-RES-16K
    6. 2542
    Prev
    Next
    INDEX
    Explanations

    phrases that express opinions or judgments, particularly involving humor or irony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eloku
    -0.38
    Véxase
    -0.37
     kirj
    -0.36
     Stelle
    -0.34
    Czytaj
    -0.33
     goutte
    -0.33
     couche
    -0.30
     comercio
    -0.30
     entera
    -0.30
     universidad
    -0.29
    POSITIVE LOGITS
    NameInMap
    0.78
     autorytatywna
    0.73
    bootstrapcdn
    0.68
    migrationBuilder
    0.65
     lenker
    0.63
     ſeinen
    0.63
     unſer
    0.63
    Selfer
    0.63
     ſeinem
    0.62
    iſchen
    0.62
    Activations Density 0.239%

    No Known Activations