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. 2678
    Prev
    Next
    INDEX
    Explanations

    references to relationships between elements in a system or framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words of conjunctions/prepositions

    np_acts-logits-general · gemini-2.0-flash

    punctuation and closing marks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </h3>
    -0.94
    </em>
    -0.72
    
    -0.71
    клопе
    -0.70
    >';
    
    -0.70
    ';
    
    -0.69
    '
    
    -0.68
    tvguidetime
    -0.67
    apimachinery
    -0.66
    '),
    
    -0.62
    POSITIVE LOGITS
    AddTagHelper
    0.80
    numerusform
    0.57
    ”).
    0.56
    ”。
    0.52
    </u>
    0.51
    ”,
    0.51
    )」
    0.51
    ”)
    0.50
    ScopeManager
    0.50
    .”.
    0.50
    Activations Density 1.556%

    No Known Activations