Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3878
    Prev
    Next
    INDEX
    Explanations

    references to colleges and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.05
    UpInside
    -0.85
    SourceChecksum
    -0.84
     Majesté
    -0.82
    SuppressMessage
    -0.82
    DispatchToProps
    -0.80
     Réponses
    -0.80
    zzleHttp
    -0.79
    
    -0.77
    adaptiveStyles
    -0.77
    POSITIVE LOGITS
     college
    2.13
     College
    2.08
     colleges
    1.84
    College
    1.82
    college
    1.79
     COLLEGE
    1.79
    COLLEGE
    1.58
     Colleges
    1.51
     Colleg
    1.17
     Collège
    1.14
    Activations Density 0.035%

    No Known Activations