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. 11305
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasting phrases that indicate a shift in argument or viewpoint

    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
     normais
    -0.58
     valmis
    -0.54
    Opal
    -0.54
     Tanner
    -0.53
     affaires
    -0.53
    ülerin
    -0.53
     finitely
    -0.52
    Dope
    -0.52
     Dink
    -0.52
    uramente
    -0.51
    POSITIVE LOGITS
     also
    1.09
    also
    0.78
     también
    0.71
     además
    0.71
     anche
    0.69
     समीक्षाओं
    0.69
     للمعارف
    0.69
    PerformLayout
    0.67
     خارجية
    0.66
     גם
    0.66
    Activations Density 0.071%

    No Known Activations