© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    references to specific academic or research citations, particularly in the context of studies or papers

    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
    ربعة
    -0.57
    ...
    -0.54
     możliwe
    -0.54
     Trost
    -0.53
     måte
    -0.52
    bný
    -0.51
    visející
    -0.50
    vábbi
    -0.50
     sledo
    -0.50
    And
    -0.49
    POSITIVE LOGITS
     JAS
    1.42
     Jamb
    1.37
     Jy
    1.33
     Ja
    1.32
     jc
    1.32
     JF
    1.30
     JJ
    1.29
     Jes
    1.29
     JM
    1.29
     JAR
    1.29
    Activations Density 0.794%

    No Known Activations