© 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 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. 12883
    Prev
    Next
    INDEX
    Explanations

    numerical data and comparisons within a context

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

    numbers and quantities

    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
     Approximately
    -1.05
    Approximately
    -1.04
     approximately
    -1.03
    approximately
    -0.98
     aproximadamente
    -0.97
    nearly
    -0.88
     yaklaşık
    -0.84
     लगभग
    -0.84
    Nearly
    -0.84
     nearly
    -0.82
    POSITIVE LOGITS
     ten
    0.91
     hundred
    0.71
     fifty
    0.69
     tenth
    0.69
     half
    0.67
     десять
    0.66
    RuleContext
    0.66
     dieci
    0.63
     zehn
    0.63
     Ten
    0.62
    Activations Density 0.457%

    No Known Activations