© 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. 22-GEMMASCOPE-RES-16K
    11. 625
    Prev
    Next
    INDEX
    Explanations

    scientific classifications, particularly related to taxonomy and species identification

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

    before suffixes (ia, ius, idis)

    np_acts-logits-general · gemini-2.0-flash

    ends with -chus, -lia, -opy, -ius, -ia, -idis, -us, -dem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     واج
    -0.48
    <eos>
    -0.48
    оле
    -0.46
    ergic
    -0.46
    hObject
    -0.44
     maf
    -0.41
    率
    -0.41
    cination
    -0.41
     relevan
    -0.40
    ¯¯
    -0.40
    POSITIVE LOGITS
     BorderRadius
    0.74
     vermelhas
    0.73
    +#+#
    0.69
     brancas
    0.69
     invokingState
    0.68
     MainAxisSize
    0.63
    sidemargin
    0.62
     verres
    0.61
     démocratie
    0.61
     caneca
    0.60
    Activations Density 0.278%

    No Known Activations