© 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. 20-GEMMASCOPE-RES-16K
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    references to Google-related terms, likely focusing on UI components

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

    Code-related, uppercase abbreviations

    np_acts-logits-general · gemini-2.0-flash

    court cases and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.81
    TemporalType
    -0.77
    帖最后由
    -0.74
    Geplaatst
    -0.73
    HasForeignKey
    -0.71
    +#+#
    -0.69
    AddWithValue
    -0.69
    ContentAlignment
    -0.67
    //
    -0.67
    mergeFrom
    -0.65
    POSITIVE LOGITS
     Diſ
    0.82
     Chriftian
    0.74
    ſelf
    0.72
     Houſe
    0.70
     Reſ
    0.69
    ſelves
    0.69
     Majefty
    0.65
     purpoſe
    0.64
     houſe
    0.62
     Chrift
    0.62
    Activations Density 0.320%

    No Known Activations