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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1119
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes in markup code

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

    class assignments

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    amaño
    -0.60
    +:+
    -0.55
    InSection
    -0.50
    تقاوى
    -0.50
    はじめに
    -0.50
    LabelTagHelper
    -0.49
    udadera
    -0.49
     row
    -0.49
    gång
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.95
     bezeichneter
    0.77
     betweenstory
    0.73
    StructEnd
    0.63
    DockStyle
    0.62
     Meksiku
    0.62
    ISupport
    0.56
    новниш
    0.56
    brigens
    0.53
    homonymie
    0.53
    Activations Density 0.021%

    No Known Activations