© 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. 275
    Prev
    Next
    INDEX
    Explanations

    names and details about individuals and their associated attributes or achievements

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

    titles or names of media works and their details

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

    identifying 'is' statements

    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
    XmlAccessType
    -0.87
    </caption>
    -0.67
     تضيفلها
    -0.66
    =$?
    -0.66
    makeText
    -0.65
    ();)
    -0.64
    ISupport
    -0.64
     فريبيس
    -0.64
    nestjs
    -0.63
     forKey
    -0.63
    POSITIVE LOGITS
     is
    1.16
     adalah
    1.05
     merupakan
    1.01
     là
    0.91
    是一
    0.79
    是一個
    0.78
     ialah
    0.77
    是
    0.76
     เป็น
    0.76
     pertenece
    0.75
    Activations Density 0.297%

    No Known Activations