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. 0-GEMMASCOPE-RES-16K
    6. 7926
    Prev
    Next
    INDEX
    Explanations

    elements related to data types and attributes in a structured document format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.53
     veda
    -0.50
    بوابة
    -0.49
    prost
    -0.48
    ỏi
    -0.47
    getDoctrine
    -0.47
     hiér
    -0.46
    LayoutStyle
    -0.46
     Wam
    -0.45
    出た
    -0.44
    POSITIVE LOGITS
     مشين
    0.93
    adaptiveStyles
    0.79
    tagHelper
    0.78
     dress
    0.75
     resourceCulture
    0.74
     Catawiki
    0.73
     slave
    0.72
     Medieval
    0.71
     wardrobe
    0.69
     statues
    0.69
    Activations Density 2.859%

    No Known Activations