© 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. 1782
    Prev
    Next
    INDEX
    Explanations

    references to monetary amounts or financial figures

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

    Year mentions

    np_acts-logits-general · gemini-2.0-flash

    years 2009-2013

    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
    DockStyle
    -0.72
     Twenty
    -0.66
    GEBURTSDATUM
    -0.66
     androidx
    -0.63
    Twenty
    -0.59
     TWENTY
    -0.57
     resourceCulture
    -0.57
    LookAnd
    -0.56
     twenty
    -0.55
    二十
    -0.54
    POSITIVE LOGITS
    MethodManager
    0.66
     tenth
    0.51
     yks
    0.50
     Tenth
    0.50
     Eleventh
    0.50
    9
    0.49
     régulière
    0.47
    createComponent
    0.46
     espelho
    0.46
     dettaglio
    0.46
    Activations Density 0.297%

    No Known Activations