© 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. 205
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal and procedural language, particularly in the context of data handling and priority claims

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

    terms related to data retrieval privileges in database management

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

    rights, claims, and privileges

    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
    Autoritní
    -0.83
     autorytatywna
    -0.77
    ItemBackground
    -0.68
     Paglinawan
    -0.66
     referenties
    -0.59
    UnitTesting
    -0.58
    InitVars
    -0.57
     cherchés
    -0.57
    abestanden
    -0.56
    ToMany
    -0.54
    POSITIVE LOGITS
     priority
    2.23
     Priority
    1.93
    priority
    1.90
    Priority
    1.85
     preference
    1.65
     prioriti
    1.61
     precedence
    1.60
     prioritized
    1.58
    优先
    1.57
     prioridad
    1.55
    Activations Density 0.329%

    No Known Activations