© 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. 15217
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences and sections

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

    Text following semicolons and other punctuation

    np_acts-logits-general · gemini-2.0-flash

    transition words

    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
    /
    -0.57
    -
    -0.52
    ,
    -0.48
    "
    -0.44
    (
    -0.43
    Xaml
    -0.43
    Okey
    -0.41
    жах
    -0.41
     Exacts
    -0.40
    .
    -0.39
    POSITIVE LOGITS
     however
    1.23
    however
    1.13
     hence
    1.06
     moreover
    1.06
    ;;;
    0.98
     furthermore
    0.94
     namely
    0.92
    hence
    0.91
     ")";
    0.90
    $;
    0.90
    Activations Density 0.142%

    No Known Activations