© 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. 3696
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, indicating the end of sentences

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

    End of sentences with citations or references

    np_acts-logits-general · gemini-2.0-flash

    references and citations

    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
    .
    -0.87
    ...
    -0.71
    ​
    -0.66
    তথ্যসূত্র
    -0.62
    (
    -0.61
    ,
    -0.60
    оборот
    -0.58
    …
    -0.57
    -
    -0.56
    "
    -0.56
    POSITIVE LOGITS
    ()].
    0.80
    ">.
    0.79
    存于互联网档案馆
    0.73
    ("%.
    0.73
    */,
    0.70
    __).
    0.70
     Esau
    0.70
     }}$.
    0.70
     <.
    0.69
     للمعارف
    0.69
    Activations Density 0.784%

    No Known Activations