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. 38829
    Prev
    Next
    INDEX
    Explanations

    references to paragraphs or sections in a document

    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
     Wur
    -0.83
     Lizzy
    -0.78
     SUA
    -0.72
    허
    -0.71
    ={`/
    -0.70
    SaveChangesAsync
    -0.69
     onCreateView
    -0.68
    kfree
    -0.68
    Ell
    -0.67
    resultCode
    -0.67
    POSITIVE LOGITS
     paragraph
    1.61
     paragraphs
    1.55
     Paragraph
    1.43
    paragraph
    1.43
    paragraphs
    1.40
    Paragraph
    1.38
     parag
    1.20
    parag
    1.02
     iParam
    0.97
     Parag
    0.96
    Activations Density 0.017%

    No Known Activations