© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure, particularly indicating the end of code blocks

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

    Before punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    capable of action or possibility

    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
     autorytatywna
    -0.79
    ValueStyle
    -0.64
     <<<<<<<<<<<<<<
    -0.61
    :✨
    -0.58
     jScrollPane
    -0.57
     насељу
    -0.55
    HasColumnType
    -0.54
     lenker
    -0.54
    SerializedName
    -0.53
    Enllaces
    -0.53
    POSITIVE LOGITS
    ↵↵
    1.17
     myſelf
    0.79
     Monfieur
    0.79
     itſelf
    0.76
     himſelf
    0.71
    ſelf
    0.68
     Theſe
    0.66
    ⠀⠀⠀⠀⠀⠀⠀⠀
    0.64
     ſta
    0.63
     Anſ
    0.63
    Activations Density 0.499%

    No Known Activations