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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 13541
    Prev
    Next
    INDEX
    Explanations

    references to historical interpretations and academic discussions related to social issues

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Shakspeare
    -0.54
     physiques
    -0.52
     roul
    -0.52
     physiologic
    -0.51
    ้ง
    -0.51
     physic
    -0.51
     đội
    -0.50
     benessere
    -0.49
     Cæsar
    -0.48
     Alman
    -0.48
    POSITIVE LOGITS
     صوتيه
    0.71
     EconPapers
    0.71
    RuleContext
    0.68
    JsonKey
    0.67
     analyses
    0.66
     scholars
    0.65
     JSTOR
    0.64
    contentLoaded
    0.63
     argued
    0.63
    Tembelea
    0.62
    Activations Density 0.461%

    No Known Activations