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. 10799
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML table structure and formatting

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

    Non-English language, code, or names

    np_acts-logits-general · gemini-2.0-flash

    Springer, heterotrophic, deepest thanks, Imaging Vendors

    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
    s
    -0.55
    bootstrapcdn
    -0.53
    annica
    -0.52
     giác
    -0.51
    Hozzáférés
    -0.51
    物
    -0.49
     Mako
    -0.49
    LEncoder
    -0.48
    </blockquote>
    -0.48
    scriptcase
    -0.44
    POSITIVE LOGITS
     Theſe
    0.74
    ]")]
    0.72
    )}_
    0.72
    "}},
    0.70
    外部链接
    0.70
    </th>
    0.69
     kaarangay
    0.68
    osaurus
    0.68
     للاسماء
    0.67
     ISNI
    0.67
    Activations Density 0.060%

    No Known Activations