© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15224
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks in written text

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

    Follows punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    numbers 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
    发表于
    -0.60
    fseek
    -0.52
    faden
    -0.48
    šky
    -0.48
     Chwiliwch
    -0.48
     whether
    -0.46
    buttonBar
    -0.46
    Rhestr
    -0.45
    UnknownFields
    -0.45
    bbene
    -0.45
    POSITIVE LOGITS
     thereby
    1.84
     Dadurch
    1.59
     thus
    1.50
    这样
    1.45
     dadurch
    1.41
     Böyle
    1.36
     így
    1.35
    これで
    1.34
     näin
    1.34
    這樣
    1.33
    Activations Density 0.431%

    No Known Activations