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. 6602
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structures in programming code

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

    Code snippets ending in ]); or });

    np_acts-logits-general · gemini-2.0-flash

    JavaScript closing syntax

    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
    </blockquote>
    -0.59
     Break
    -0.54
    </h4>
    -0.52
     disambiguazione
    -0.50
     break
    -0.48
     means
    -0.46
    gameserver
    -0.46
    tvguidetime
    -0.44
    例文帳に追加
    -0.43
    setVerticalGroup
    -0.42
    POSITIVE LOGITS
    >)</
    0.79
    ”).
    0.79
    });
    0.78
    `);
    0.76
    });
    
    0.75
    .”)
    0.75
    })
    0.75
    ”),
    0.74
    });*/
    0.73
    $),
    0.72
    Activations Density 0.063%

    No Known Activations