© 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. 13-GEMMASCOPE-RES-65K
    6. 22337
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun "our" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -1.13
     propOrder
    -1.05
    enumii
    -0.99
    MessageTagHelper
    -0.96
    CloseOperation
    -0.95
    RenderAtEndOf
    -0.93
    SharedDtor
    -0.93
     nahilalakip
    -0.91
     CreateTagHelper
    -0.89
    RetentionPolicy
    -0.88
    POSITIVE LOGITS
     “
    0.69
     
    0.67
     popular
    0.64
     ‘
    0.63
     mini
    0.63
     latest
    0.62
     "
    0.58
     two
    0.55
     Goldberg
    0.55
     «
    0.54
    Activations Density 0.035%

    No Known Activations