Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15099
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Stephen Colbert" or references associated with him

    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
     Rocking
    -0.74
    Witt
    -0.72
     Canva
    -0.72
    Imo
    -0.69
    isfile
    -0.69
    divarius
    -0.69
     Malang
    -0.69
    igsaw
    -0.69
     BioLib
    -0.68
     Lass
    -0.68
    POSITIVE LOGITS
    PHEN
    1.44
     Stephen
    1.41
     Stephens
    1.21
    stephen
    1.20
     STEPHEN
    1.20
    Stephen
    1.19
     stephen
    1.15
     Steph
    1.09
    Steph
    1.01
     Stephan
    0.97
    Activations Density 0.011%

    No Known Activations