© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 31
    Prev
    Next
    INDEX
    Explanations

    affirmative expressions of assurance or confidence

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

    terms related to guarantees and assurances

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

    assurance that

    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
     Audiodateien
    -0.62
     Matos
    -0.55
    jois
    -0.54
    ingual
    -0.53
    etzal
    -0.52
     Unito
    -0.52
    ::__
    -0.51
     aident
    -0.49
     wherefore
    -0.49
    †
    -0.49
    POSITIVE LOGITS
    makeConstraints
    0.89
     assuré
    0.78
     assurances
    0.77
     rằng
    0.77
    assurance
    0.76
     InputDecoration
    0.75
     חיצוניים
    0.74
    assured
    0.72
    клопе
    0.71
    MLLoader
    0.70
    Activations Density 0.006%

    No Known Activations