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. 12788
    Prev
    Next
    INDEX
    Explanations

    references to statistical metrics and player attributes related to sports performance

    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
     للمعارف
    -0.71
     indisponible
    -0.63
    Jeografia
    -0.58
    ++
    
    -0.58
    geted
    -0.55
    ğraf
    -0.54
    </caption>
    -0.53
     best
    -0.50
    FieldBuilder
    -0.49
     allAfrica
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.61
     CommonModule
    0.53
     säll
    0.52
    ictwo
    0.51
     newOwner
    0.51
     bassi
    0.51
    istoitu
    0.51
     quelquefois
    0.50
     mView
    0.50
     skimage
    0.49
    Activations Density 0.028%

    No Known Activations