© 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. 11-GEMMASCOPE-RES-16K
    11. 9198
    Prev
    Next
    INDEX
    Explanations

    sentences containing advice or warnings regarding health and safety

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    PhysRev
    -0.52
     Nego
    -0.52
    ân
    -0.51
     umum
    -0.51
     COMPONENT
    -0.51
    ,:);
    -0.51
     Ditto
    -0.51
    CTYPE
    -0.48
    COMPONENT
    -0.48
     nød
    -0.48
    POSITIVE LOGITS
    клопе
    0.59
    kháu
    0.59
    المناصب
    0.56
    těte
    0.56
     referrerpolicy
    0.54
     mergeFrom
    0.52
    lesias
    0.52
    IntoConstraints
    0.51
     visitó
    0.50
    stdc
    0.50
    Activations Density 0.237%

    No Known Activations