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. 5-GEMMASCOPE-RES-16K
    6. 10431
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives indicating intensity or degree

    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
    Життєпис
    -0.72
    esModule
    -0.72
     يتيمه
    -0.70
    terness
    -0.69
    имущества
    -0.68
    endphp
    -0.67
     للمعارف
    -0.66
     préféré
    -0.66
    )="
    -0.66
     ويكيميديا
    -0.65
    POSITIVE LOGITS
     autant
    0.73
     as
    0.68
    DrawerToggle
    0.59
     than
    0.58
    Geografie
    0.52
     quanto
    0.49
     kuin
    0.49
    WindowConstants
    0.49
    pyplot
    0.48
     nahilalakip
    0.47
    Activations Density 0.102%

    No Known Activations