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. 5-GEMMASCOPE-RES-16K
    6. 3899
    Prev
    Next
    INDEX
    Explanations

    instances of strong document structure or identifiable sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.67
     كومونز
    -0.64
     Goldberg
    -0.63
    icza
    -0.63
    значение
    -0.62
    Hentet
    -0.62
    artz
    -0.60
    arate
    -0.59
    "][
    -0.58
    Demografia
    -0.57
    POSITIVE LOGITS
    \
    1.06
    itemize
    0.79
    </tr>
    0.78
    !*\
    0.77
    ,'\
    0.76
    </thead>
    0.72
    archiviato
    0.70
    )\
    0.69
     reaſon
    0.69
     дописавши
    0.69
    Activations Density 0.003%

    No Known Activations