© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    instances of specific formatting or placeholder tokens in text

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    questions starting with Q:

    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
    OGND
    -0.73
    setopt
    -0.68
    tagHelperRunner
    -0.66
    ----</
    -0.65
    LookAnd
    -0.65
     متعلقه
    -0.59
    ViewById
    -0.59
     intptr
    -0.58
    less
    -0.56
    expandindo
    -0.55
    POSITIVE LOGITS
     slutt
    0.51
     przeci
    0.48
    NECT
    0.48
     épreuves
    0.47
     इसके
    0.46
     상세
    0.46
    TypedDataSet
    0.46
     useAppContext
    0.45
     gjerne
    0.45
     Fortunately
    0.44
    Activations Density 0.031%

    No Known Activations