© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82130
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate uncertainty or potential outcomes

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

    expresses possibility

    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
     Wikimedijinoj
    -0.40
    好像
    -0.39
    PropertyChanging
    -0.38
    可
    -0.37
    有时
    -0.36
    niająca
    -0.36
     kus
    -0.34
    原标题
    -0.34
    ЧЕСКИ
    -0.34
    ertas
    -0.34
    POSITIVE LOGITS
     could
    1.94
    Could
    1.73
    could
    1.70
     Could
    1.63
     COULD
    1.38
     podría
    1.27
     poderia
    1.27
     pourraient
    1.21
     könnten
    1.19
     pourrait
    1.18
    Activations Density 0.095%

    No Known Activations