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. 5-GEMMASCOPE-RES-16K
    6. 16021
    Prev
    Next
    INDEX
    Explanations

    the presence of anchor tags and buttons associated with hyperlinks and navigation

    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
    tvguidetime
    -0.77
    RepeatedField
    -0.75
    GEBURTSDATUM
    -0.73
     itſelf
    -0.70
     endregion
    -0.69
     Monfieur
    -0.65
     تانيه
    -0.65
     Diſ
    -0.65
     Conſ
    -0.65
    
    -0.64
    POSITIVE LOGITS
     href
    1.06
    a
    0.99
     Link
    0.92
     link
    0.88
    Link
    0.87
    NavLink
    0.83
    UrlResolution
    0.76
    link
    0.72
     enlace
    0.69
     links
    0.68
    Activations Density 0.047%

    No Known Activations