© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1526
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know."

    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
     '{@
    -0.57
    язы
    -0.57
     nadie
    -0.55
    yet
    -0.54
    uxley
    -0.54
    ̈́
    -0.53
     CreateTagHelper
    -0.53
     صوتيه
    -0.52
     termino
    -0.51
     THOUGH
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.72
    Hentet
    0.66
     thụ
    0.65
    Geplaatst
    0.62
     esterni
    0.61
     برانيه
    0.56
    tură
    0.56
    umina
    0.56
    Abitanti
    0.55
    makeText
    0.55
    Activations Density 0.056%

    No Known Activations