© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14612
    Prev
    Next
    INDEX
    Explanations

    HTML or markup elements, specifically block quotes

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

    HTML or code block delimiters

    np_acts-logits-general · gemini-2.0-flash

    code prompts and replies

    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
     bezeichneter
    -0.82
     dot
    -0.74
    Amicalement
    -0.70
     par
    -0.70
     ber
    -0.70
    Mvh
    -0.69
    usermodel
    -0.68
     le
    -0.66
    ",&
    -0.65
     po
    -0.65
    POSITIVE LOGITS
    <blockquote>
    1.52
    <h4>
    1.14
    <h3>
    1.13
    <h5>
    1.11
     itſelf
    1.07
     Houſe
    1.00
     alſo
    0.99
    <h1>
    0.98
     ſhe
    0.97
     greateſt
    0.96
    Activations Density 0.015%

    No Known Activations