© 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. 22-GEMMASCOPE-RES-16K
    11. 4611
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their structural components

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

    Chemical or organic compound fragments

    np_acts-logits-general · gemini-2.0-flash

    chemical names

    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
    celi
    -0.60
    iesis
    -0.59
    ESTE
    -0.55
    ULLY
    -0.53
    स्तु
    -0.50
    otea
    -0.49
    </tfoot>
    -0.49
    oches
    -0.49
    chauer
    -0.48
     bli
    -0.48
    POSITIVE LOGITS
    出版年
    0.72
    parsedMessage
    0.72
     ſon
    0.70
     Majefty
    0.70
    RectangleBorder
    0.70
     Diſ
    0.69
     Reſ
    0.68
     Perſ
    0.68
     Efq
    0.68
     Jefus
    0.67
    Activations Density 0.855%

    No Known Activations