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. 14345
    Prev
    Next
    INDEX
    Explanations

    headings or subheadings within 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
    moud
    -0.84
    madol
    -0.81
     FormsModule
    -0.79
     Ares
    -0.77
     Beaumont
    -0.77
     Padilla
    -0.74
     TMS
    -0.74
    ItemModel
    -0.73
     saree
    -0.71
     Chandler
    -0.71
    POSITIVE LOGITS
    <h4>
    1.96
    theless
    1.01
    strptime
    0.93
     ####
    0.90
    FormTagHelper
    0.80
    endregion
    0.79
    Спасылкі
    0.76
    Kapcsolódó
    0.75
     دیکھیے
    0.74
    edig
    0.74
    Activations Density 0.116%

    No Known Activations