© 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. 14981
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to graphical formatting and layout in a structured document

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

    Mathematical/statistical symbols or code

    np_acts-logits-general · gemini-2.0-flash

    assignments or equality checks

    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
    IUrlHelper
    -0.57
    тифика
    -0.56
    endphp
    -0.55
     @"/
    -0.55
    swick
    -0.55
    aderie
    -0.53
    alleria
    -0.53
    FECT
    -0.49
     xoay
    -0.49
    diyah
    -0.48
    POSITIVE LOGITS
     =
    1.11
    =
    1.03
     ==
    0.79
     = 
    0.78
     $=
    0.76
     ===
    0.76
    >=</
    0.75
     is
    0.71
     :=
    0.70
    =\
    0.69
    Activations Density 0.262%

    No Known Activations