© 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. 3943
    Prev
    Next
    INDEX
    Explanations

    references to computing systems and technologies

    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
     disponibilités
    -0.64
    ()");
    -0.62
    SEGUIR
    -0.61
    GEBURTSDATUM
    -0.61
     commandés
    -0.58
    engertian
    -0.55
     étoient
    -0.55
    /";
    -0.53
    /';
    -0.53
     åp
    -0.53
    POSITIVE LOGITS
     BTW
    1.33
    brigens
    1.27
     btw
    1.26
     incidentally
    1.19
    BTW
    1.16
    Кстати
    1.15
    Btw
    1.06
     Incidentally
    1.03
    btw
    1.02
     übrigens
    0.98
    Activations Density 0.283%

    No Known Activations