© 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. 5748
    Prev
    Next
    INDEX
    Explanations

    experimental protocols related to biochemical assays

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

    Past-tense verbs related to scientific experimentation

    np_acts-logits-general · gemini-2.0-flash

    scientific measurement and analysis

    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
     even
    -0.79
     might
    -0.68
     maybe
    -0.68
     perhaps
    -0.67
     vielleicht
    -0.67
     magari
    -0.66
     Even
    -0.65
     Perhaps
    -0.63
    Even
    -0.63
    perhaps
    -0.62
    POSITIVE LOGITS
    AndEndTag
    0.78
     triplicate
    0.71
     underwent
    0.70
     consisted
    0.69
     separately
    0.69
     jeweils
    0.68
     respectively
    0.68
     Subsequently
    0.67
    respectively
    0.67
     Roskov
    0.66
    Activations Density 3.652%

    No Known Activations