© 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. 0-GEMMASCOPE-RES-65K
    6. 9722
    Prev
    Next
    INDEX
    Explanations

    references to items or entities that are associated with guns or weaponry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exploratory
    -0.52
     Doreen
    -0.50
    ulan
    -0.49
     owls
    -0.47
    Ten
    -0.47
    nen
    -0.45
     Ferri
    -0.45
     acredit
    -0.45
     Перед
    -0.44
    My
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    1.17
    OGND
    1.15
    GEBURTSDATUM
    1.13
     שוליים
    0.95
    mybatisplus
    0.92
    ValueStyle
    0.90
    NameInMap
    0.88
     resourceCulture
    0.87
     ModelExpression
    0.84
    DeleteBehavior
    0.84
    Activations Density 0.045%

    No Known Activations