© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistical significance and related analyses

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

    was considered significant

    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
    ่านั้น
    -0.39
    enumii
    -0.36
     Sonn
    -0.34
     Begle
    -0.30
     kereszt
    -0.29
     parvenir
    -0.29
     Bege
    -0.28
     demonstrates
    -0.27
     plurality
    -0.27
     tromper
    -0.27
    POSITIVE LOGITS
     assumed
    1.30
    assumed
    1.17
     chosen
    1.09
     assume
    1.01
     considered
    0.99
     arbitrarily
    0.95
    chosen
    0.94
     adopted
    0.94
     consideramos
    0.93
     assumes
    0.92
    Activations Density 0.447%

    No Known Activations