© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and function declarations

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

    Code block beginnings (if, class, def)

    np_acts-logits-general · gemini-2.0-flash

    code blocks and function definitions

    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
     ویکی‌پدیا
    -0.49
    $
    -0.48
    하면
    -0.48
    findpost
    -0.47
    圳
    -0.47
     appelez
    -0.46
    NewRow
    -0.46
    istoitu
    -0.45
     nuages
    -0.43
    Về
    -0.43
    POSITIVE LOGITS
     "..\..\..\
    0.76
     "..\..\
    0.70
     <<<<<<<<<<<<<<
    0.66
    def
    0.64
    Jeografia
    0.63
    InvalidProtocol
    0.62
    setupUi
    0.62
     doInBackground
    0.61
    :✨
    0.60
    󠁢
    0.59
    Activations Density 0.037%

    No Known Activations