© 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. 14920
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of authors and researchers in the context of academic references

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

    Text within parentheses

    np_acts-logits-general · gemini-2.0-flash

    citation names and punctuation

    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
    ^(@)
    -1.00
    SharedCtor
    -0.90
    */;
    -0.88
     */;
    -0.84
    verwijspagina
    -0.84
     linkovi
    -0.82
     Савезне
    -0.82
    %")
    -0.82
     وتسجيلات
    -0.80
    \"></
    -0.79
    POSITIVE LOGITS
     ed
    0.85
     (
    0.76
    .
    0.76
     et
    0.71
     "
    0.70
     
    0.65
     biên
    0.61
     eds
    0.61
    :
    0.60
     “
    0.57
    Activations Density 0.454%

    No Known Activations