© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15181
    Prev
    Next
    INDEX
    Explanations

    references to mathematical functions and values

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

    `Math` followed by `.`

    np_acts-logits-general · gemini-2.0-flash

    programming function calls with `.`

    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
    AndroidJUnit
    -0.57
     “
    -0.56
    mouseleave
    -0.54
    =@"
    -0.49
    ()));
    -0.47
    ()]);
    -0.46
    HttpPut
    -0.45
     ‘
    -0.45
     The
    -0.45
    après
    -0.44
    POSITIVE LOGITS
     الدولى
    0.79
    LEncoder
    0.76
    ScopeManager
    0.74
    AxisAlignment
    0.73
     disponibilités
    0.71
     GoogleFonts
    0.69
     المعيارى
    0.69
    Compat
    0.67
    vician
    0.64
    ंदीखरीदारी
    0.64
    Activations Density 0.087%

    No Known Activations