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. 7392
    Prev
    Next
    INDEX
    Explanations

    inquiries related to measurements and comparisons of values or identities

    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
     "")
    
    -1.00
     "");
    
    -0.92
    '),
    
    -0.88
    '))
    
    -0.88
    ++
    
    -0.86
     "").
    -0.86
    '];
    
    -0.85
    .")
    
    -0.85
    ()].
    -0.84
    .");
    
    -0.82
    POSITIVE LOGITS
    
    0.66
     дописавши
    0.63
     виправивши
    0.61
    <()>
    0.53
     Wallflower
    0.50
    ">
    0.49
    felves
    0.45
    '>
    0.45
    makeConstraints
    0.43
    appliquent
    0.42
    Activations Density 0.304%

    No Known Activations