Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1745
    Prev
    Next
    INDEX
    Explanations

    sections of text that include specific references to programming or technical terms

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    z as a mathematical variable

    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
    yntaxException
    -0.72
     thither
    -0.62
    rawdę
    -0.59
    enderror
    -0.57
    ElementException
    -0.56
     rağmen
    -0.54
    /−
    -0.54
    iconque
    -0.54
     zamanda
    -0.54
    lığ
    -0.53
    POSITIVE LOGITS
    sizeCache
    0.52
    GIVEREF
    0.52
    ulas
    0.50
    SuspendLayout
    0.49
    indy
    0.49
    parsedMessage
    0.48
    jsxFileName
    0.48
    lec
    0.47
     check
    0.47
     Paper
    0.46
    Activations Density 0.016%

    No Known Activations