© 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. 11-GEMMASCOPE-RES-16K
    11. 4737
    Prev
    Next
    INDEX
    Explanations

    the presence of tabs used to delineate data entries or structures in a formatted document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -1.07
     iſt
    -0.94
     dieß
    -0.93
     auffi
    -0.93
     niedersachsen
    -0.89
     faſt
    -0.88
     pleaſure
    -0.85
     öffnungszeiten
    -0.85
     againſt
    -0.83
    ſelf
    -0.83
    POSITIVE LOGITS
     
    1.67
    mathrm
    0.75
     $
    0.75
    フェクト
    0.68
     
    0.65
      (
    0.64
     L
    0.64
    tigungs
    0.63
     K
    0.63
     T
    0.62
    Activations Density 1.755%

    No Known Activations