© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 12645
    Prev
    Next
    INDEX
    Explanations

    the word "se" which likely indicates a focus on the second person singular/plural pronoun or a type of punctuation

    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
     AssemblyProduct
    -0.70
    ValueStyle
    -0.69
    principalColumn
    -0.66
    AddTagHelper
    -0.58
    styleType
    -0.56
    Program
    -0.54
    vertisers
    -0.54
    TargetException
    -0.54
     Thra
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
    se
    1.33
     majority
    1.08
    majority
    1.02
     maioria
    0.97
     Majority
    0.95
     majorité
    0.93
    Majority
    0.90
    seat
    0.85
     mayoría
    0.85
     Seat
    0.83
    Activations Density 0.071%

    No Known Activations