© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    elements representing mathematical or programming syntax

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

    Followed by the letter 'b'

    np_acts-logits-general · gemini-2.0-flash

    a, b, c, or d

    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
    Хьажоргаш
    -0.66
     Wikimedijinoj
    -0.64
    reportWebVitals
    -0.59
    GrantedAuthority
    -0.58
     Савезне
    -0.56
     odkazy
    -0.56
     HttpHeaders
    -0.55
    fromnode
    -0.55
     jadx
    -0.54
    Vidite
    -0.54
    POSITIVE LOGITS
     b
    0.99
    b
    0.85
     B
    0.82
    B
    0.69
     getB
    0.66
     ویکی‌پدیای
    0.66
    ｂ
    0.64
     A
    0.61
    getB
    0.58
    ب
    0.52
    Activations Density 0.375%

    No Known Activations