Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1510
    Prev
    Next
    INDEX
    Explanations

    references to time management and scheduling features

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

    HTML tags: </code>, </strong>, </em>, </u>, </h2>

    np_acts-logits-general · gemini-2.0-flash

    HTML closing tags

    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
     Roskov
    -0.92
    ValueStyle
    -0.88
    Chham
    -0.85
    <eos>
    -0.74
     Bioaccumulative
    -0.73
    expandindo
    -0.73
     '\\;'
    -0.72
    adpleegd
    -0.72
    richTextPanel
    -0.71
    ніципалі
    -0.71
    POSITIVE LOGITS
    </strong>
    3.25
    </em>
    2.58
    </b>
    2.57
    </u>
    2.56
    </h2>
    2.32
    </code>
    1.98
    </h4>
    1.97
    </h3>
    1.95
    </i>
    1.94
    </sub>
    1.61
    Activations Density 0.989%

    No Known Activations