© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure elements

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    legal notifications and political party names

    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
     infine
    -0.65
     again
    -0.60
     another
    -0.60
    <eos>
    -0.59
     I
    -0.58
     other
    -0.55
     he
    -0.54
     we
    -0.53
    .
    -0.52
     lastly
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.99
    TagMode
    0.97
     Efq
    0.92
     Administrativna
    0.85
    tagHelperRunner
    0.84
    setVerticalGroup
    0.82
     ostavi
    0.82
    IsContent
    0.81
    bewerken
    0.80
    ſelf
    0.80
    Activations Density 0.243%

    No Known Activations