© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    content related to popularity or widely recognized subjects

    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
     
    -0.72
    ள்
    -0.65
     niega
    -0.64
     Sek
    -0.61
    ValueStyle
    -0.60
     τ
    -0.60
    gms
    -0.59
     c
    -0.58
     cu
    -0.58
     Biss
    -0.58
    POSITIVE LOGITS
     Efq
    1.62
     pleaſure
    1.58
     Theſe
    1.55
     myſelf
    1.55
     Jefus
    1.53
     Monfieur
    1.47
     themſelves
    1.47
     whoſe
    1.42
     Majefty
    1.42
     himſelf
    1.41
    Activations Density 0.037%

    No Known Activations