© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    code structures or syntax related to the main function and object-oriented programming features

    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
     coupon
    -0.67
     vouchers
    -0.61
     coupons
    -0.57
     voucher
    -0.57
     Coupon
    -0.55
    idez
    -0.55
    uber
    -0.55
    ubert
    -0.53
     Bonif
    -0.53
    Coupon
    -0.52
    POSITIVE LOGITS
    __':
    3.37
    __':
    3.30
    __":
    3.29
    __":
    3.23
    +#+#
    1.15
    ArgsConstructor
    1.10
    \{\\
    1.08
    новништво
    1.01
    ).__
    0.99
    Sucesor
    0.98
    Activations Density 0.005%

    No Known Activations