© 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. 16-GEMMASCOPE-RES-16K
    11. 4285
    Prev
    Next
    INDEX
    Explanations

    references to existing categories or classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "The" or a capital letter word

    np_acts-logits-general · gemini-2.0-flash

    Combine strings and bit lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vérit
    -0.80
     épaules
    -0.79
     pouvoirs
    -0.77
     lèvres
    -0.73
     leçons
    -0.73
     vœux
    -0.73
     gouvernements
    -0.73
     négociations
    -0.72
     démocr
    -0.71
     renseignements
    -0.71
    POSITIVE LOGITS
     these
    0.80
    these
    0.71
     those
    0.69
     theses
    0.65
    tols
    0.64
    These
    0.64
     các
    0.62
     These
    0.61
    iths
    0.61
    ospels
    0.60
    Activations Density 0.601%

    No Known Activations