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. 7545
    Prev
    Next
    INDEX
    Explanations

    structured data elements and attributes in code

    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
     vectorielles
    -0.54
    이터
    -0.51
     souris
    -0.50
     élevées
    -0.50
     åt
    -0.50
     quelcon
    -0.48
     Lettres
    -0.47
     supérieures
    -0.46
     således
    -0.46
     aussitôt
    -0.46
    POSITIVE LOGITS
    jScrollPane
    0.72
     location
    0.69
     nature
    0.67
     type
    0.66
     duration
    0.66
    remarks
    0.63
     gender
    0.63
     notes
    0.62
    备注
    0.62
     Remarks
    0.62
    Activations Density 0.200%

    No Known Activations