© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1587
    Prev
    Next
    INDEX
    Explanations

    keywords related to app licensing and compliance

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

    references to software applications or licenses

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

    legal citations ending with App

    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
     from
    -0.44
    bey
    -0.42
    nia
    -0.38
    log
    -0.36
    das
    -0.35
    popo
    -0.35
    uden
    -0.34
    uria
    -0.34
    ండ
    -0.34
     refer
    -0.33
    POSITIVE LOGITS
    expandindo
    1.04
    MigrationBuilder
    0.92
    ⓧ
    0.89
     ویکی‌پدی
    0.88
     '\\;'
    0.88
     saites
    0.85
     ***!
    0.85
    +#+#
    0.83
    migrationBuilder
    0.83
     Roskov
    0.82
    Activations Density 0.095%

    No Known Activations