© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1108
    Prev
    Next
    INDEX
    Explanations

    the word "t" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     business
    -0.58
     Dooley
    -0.57
     do
    -0.56
     dob
    -0.54
     biz
    -0.54
     Verne
    -0.54
    konom
    -0.52
     Rox
    -0.52
     Business
    -0.52
     setId
    -0.51
    POSITIVE LOGITS
     isnt
    0.96
     isn
    0.86
     is
    0.80
    تقاوى
    0.78
    GEBURTSDATUM
    0.75
     wasnt
    0.75
    Portale
    0.75
     linkovi
    0.73
     shouldBe
    0.72
    ίναι
    0.71
    Activations Density 0.033%

    No Known Activations