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. 4199
    Prev
    Next
    INDEX
    Explanations

    racing outcomes and statistics

    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
     ]];
    -0.64
    uidado
    -0.64
    Портал
    -0.60
    }');
    -0.60
    agaimana
    -0.58
    >");
    
    -0.57
     springfox
    -0.57
    saraba
    -0.57
     ThemeData
    -0.56
    ,:);
    -0.56
    POSITIVE LOGITS
     withdrew
    0.72
     forfeit
    0.69
     disqualified
    0.65
     missed
    0.60
     Walkover
    0.59
     forfeited
    0.57
     scratched
    0.56
     withdrawn
    0.56
    DNS
    0.56
    missed
    0.55
    Activations Density 0.132%

    No Known Activations