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. 12133
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and permissions

    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
    XmlAccessorType
    -0.48
    Regressor
    -0.44
    henswürdigkeiten
    -0.43
    npmjs
    -0.42
    RenderAtEndOf
    -0.41
     regulares
    -0.41
     improvised
    -0.41
     تشکیل
    -0.39
    wayat
    -0.38
     msglen
    -0.38
    POSITIVE LOGITS
     copyright
    1.30
     licensing
    1.14
    copyright
    1.05
     license
    1.04
     royalty
    1.00
     Copyright
    0.98
     licence
    0.97
     royalties
    0.97
    license
    0.96
     Licensing
    0.96
    Activations Density 0.323%

    No Known Activations