© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13
    Prev
    Next
    INDEX
    Explanations

    references to social media privacy issues and verification processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    foreign language contexts

    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
    Negative Logits
    يون
    -0.61
    riebene
    -0.56
    ська
    -0.49
    chtete
    -0.48
    obviously
    -0.48
    suke
    -0.48
    nowe
    -0.48
    лая
    -0.48
    الدرا
    -0.48
    ländische
    -0.48
    POSITIVE LOGITS
    abestanden
    0.67
    EndContext
    0.61
    providedIn
    0.61
     Económica
    0.60
    verwijspagina
    0.60
     estekak
    0.58
    Geplaatst
    0.58
     resourceCulture
    0.56
     referenties
    0.56
    يكب
    0.51
    Activations Density 0.057%

    No Known Activations