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. 2195
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to text formatting, such as size, height, and alignment

    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
     @"/
    -0.70
     ostavi
    -0.68
    évaluateur
    -0.68
     referenties
    -0.63
     localVar
    -0.61
     dreapta
    -0.59
     Mep
    -0.56
    슷
    -0.54
     mData
    -0.53
    ')):
    -0.52
    POSITIVE LOGITS
    size
    1.15
     size
    1.04
    fontSize
    1.01
    sized
    0.92
    FontSize
    0.85
     sized
    0.83
     fontSize
    0.81
    SIZE
    0.74
    indd
    0.74
     الاطلاع
    0.71
    Activations Density 0.032%

    No Known Activations