© 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 EvalsExportsAPI 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. 1173
    Prev
    Next
    INDEX
    Explanations

    references to the Voigt profile and its applications in scientific contexts

    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
    AndEndTag
    -0.82
     Badger
    -0.72
     Vile
    -0.68
    Badger
    -0.67
    ValueStyle
    -0.64
    Duplicates
    -0.64
     shur
    -0.63
    tine
    -0.62
    Географиясе
    -0.61
    "]];
    -0.61
    POSITIVE LOGITS
    vo
    2.84
     Vo
    2.65
     vo
    2.61
    Vo
    2.58
    VO
    2.42
     VO
    2.17
    во
    1.50
    vos
    1.40
     Voss
    1.35
    wo
    1.30
    Activations Density 0.134%

    No Known Activations