© 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. 20-GEMMASCOPE-RES-16K
    11. 14788
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in the code snippets

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

    Code comments or directives

    np_acts-logits-general · gemini-2.0-flash

    code comments and following actions

    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
     itſelf
    -0.81
    Билгалдахарш
    -0.81
    IsPostBack
    -0.75
     Majefty
    -0.75
     Мексичка
    -0.75
     Efq
    -0.75
     linkovi
    -0.74
     BigNumberish
    -0.74
     conftest
    -0.73
    extAlignment
    -0.72
    POSITIVE LOGITS
     get
    0.76
     Get
    0.74
     Now
    0.69
     check
    0.68
     now
    0.67
     بيها
    0.66
     The
    0.63
     First
    0.62
    #+#
    0.62
     Here
    0.61
    Activations Density 0.094%

    No Known Activations