© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 2251
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gem" and its variations, indicating a focus on valuable or noteworthy items or concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     
    -0.60
     &___
    -0.56
     I
    -0.56
     N
    -0.55
    ↵↵
    -0.54
    LayoutStyle
    -0.54
    encodeWith
    -0.53
    typedef
    -0.53
    帖最后由
    -0.52
     (
    -0.52
    POSITIVE LOGITS
     pleaſure
    1.24
     Monfieur
    1.22
     Efq
    1.16
     itſelf
    1.11
     Jefus
    1.10
     himſelf
    1.05
     Majefty
    1.05
     greateſt
    1.04
     whoſe
    1.04
     ſtate
    1.02
    Activations Density 0.290%

    No Known Activations