© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to methodologies and their applications

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

    followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    modal verbs + past participle

    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
    +#+
    -0.56
    strdup
    -0.55
    googleapis
    -0.55
     EconPapers
    -0.53
    <!--[
    -0.52
     transfieras
    -0.51
    ніципалі
    -0.51
    Didn
    -0.51
     there
    -0.51
    endforeach
    -0.50
    POSITIVE LOGITS
     was
    1.08
     veniva
    0.95
     został
    0.94
     été
    0.94
     být
    0.93
     została
    0.93
     être
    0.92
     được
    0.90
     zostało
    0.85
     zostanie
    0.85
    Activations Density 1.649%

    No Known Activations