© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 22049
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "as" in various contexts

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

    describing something as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.45
    الإنجليزية
    -0.40
     (;;)
    -0.38
     Lordships
    -0.36
    :^(
    -0.35
     koska
    -0.35
    SharedCtor
    -0.34
     todėl
    -0.33
     grâce
    -0.32
     própria
    -0.32
    POSITIVE LOGITS
     viewed
    0.85
     seen
    0.77
     portrayed
    0.71
    viewed
    0.69
     played
    0.68
     expressed
    0.66
     conceived
    0.66
     interpreted
    0.63
     conducted
    0.63
    seen
    0.63
    Activations Density 0.060%

    No Known Activations