© 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. 20-GEMMASCOPE-RES-16K
    6. 10856
    Prev
    Next
    INDEX
    Explanations

    references to bodily sensations and physical states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific or medical terminology related to neurological, psychological, or pharmacological studies.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    strophic
    -0.44
    SerializeField
    -0.43
     čast
    -0.42
     Nachhaltigkeit
    -0.41
     Gründung
    -0.41
    GEBURTSDATUM
    -0.40
    KommentareTeilen
    -0.39
     Harbour
    -0.39
    apimachinery
    -0.37
     caminhão
    -0.37
    POSITIVE LOGITS
     feeling
    0.55
     للاسماء
    0.53
     hangover
    0.52
     <=",
    0.50
    feel
    0.49
     feel
    0.49
     mood
    0.48
     emotion
    0.48
     feels
    0.47
    feeling
    0.47
    Activations Density 0.235%

    No Known Activations