© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15809
    Prev
    Next
    INDEX
    Explanations

    elements related to object or data structure declarations and manipulations

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

    Followed by "w", "l", "f", "t", or "R"

    np_acts-logits-general · gemini-2.0-flash

    l, w, and r

    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
    Xna
    -0.67
    Portale
    -0.66
    WireFormatLite
    -0.60
    EndGlobalSection
    -0.58
    ConfigureAwait
    -0.57
     Hej
    -0.57
     ujednoznacz
    -0.57
    PerformLayout
    -0.56
    EditorBrowsable
    -0.55
    iredo
    -0.55
    POSITIVE LOGITS
     W
    0.70
     S
    0.70
     M
    0.68
     L
    0.68
     R
    0.65
     N
    0.61
     T
    0.59
    vų
    0.56
     U
    0.55
     Q
    0.55
    Activations Density 0.760%

    No Known Activations