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. 20-GEMMASCOPE-RES-16K
    6. 12560
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vikipedi
    -0.61
    +:+
    -0.60
    HasAnnotation
    -0.58
    GraphicsUnit
    -0.57
     appunto
    -0.56
     =>'
    -0.55
     chiunque
    -0.54
    !...
    -0.54
     intptr
    -0.54
    TokenNameLPAREN
    -0.53
    POSITIVE LOGITS
    <?
    0.61
     Sulfate
    0.58
     MUSIC
    0.58
     Music
    0.57
     electr
    0.57
     music
    0.56
     Chomsky
    0.55
    écou
    0.55
    iotensin
    0.55
     color
    0.55
    Activations Density 2.695%

    No Known Activations