© 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. 23-GEMMASCOPE-RES-16K
    6. 9886
    Prev
    Next
    INDEX
    Explanations

    references to food and dining, particularly in cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     старости
    -0.32
     تحقق
    -0.31
    <!--[
    -0.29
    実現
    -0.29
     continuing
    -0.29
    assertIn
    -0.28
     giàu
    -0.28
     zda
    -0.27
    fn
    -0.27
     theo
    -0.27
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    styleable
    0.61
    thalene
    0.60
     autorytatywna
    0.56
     advertisements
    0.56
    VERTIS
    0.55
    stuffs
    0.54
     AppCompatTheme
    0.54
    chyma
    0.53
    IntoConstraints
    0.53
    Activations Density 0.160%

    No Known Activations