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. 20-GEMMASCOPE-RES-16K
    6. 2006
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the end of sentences

    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
    <bos>
    -0.91
     autorytatywna
    -0.85
     كومونز
    -0.83
    出版年
    -0.82
    脚注の使い方
    -0.82
     насељу
    -0.78
    tvguidetime
    -0.77
    %;
    
    -0.77
    WithIOException
    -0.74
     ';
    
    -0.74
    POSITIVE LOGITS
    ↵↵
    1.12
    ↵↵↵
    0.82
    <eos>
    0.74
    </tbody>
    0.67
    </tr>
    0.63
    ↵↵↵↵
    0.61
    ↵↵↵↵↵
    0.60
    ↵
    0.58
    </h2>
    0.53
    なお
    0.52
    Activations Density 0.653%

    No Known Activations