© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    references to royal events and celebrities

    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
     daß
    -0.56
     généraux
    -0.55
     skall
    -0.51
     idéia
    -0.51
    ReusableCell
    -0.49
    uanto
    -0.48
     General
    -0.47
    onomic
    -0.47
     Einfluß
    -0.47
     familles
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.83
     netizens
    0.71
     ⁠
    0.71
    providedIn
    0.71
     depic
    0.70
    RegressionTest
    0.69
     emojis
    0.68
    SpringBootTest
    0.67
    IUrlHelper
    0.67
     downvotes
    0.65
    Activations Density 0.077%

    No Known Activations