Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 4700
    Prev
    Next
    INDEX
    Explanations

    references to Huntington's disease and related medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserRouter
    -0.92
     MCM
    -0.92
     Placer
    -0.92
     Alton
    -0.89
    MCM
    -0.87
     Sph
    -0.87
     boobs
    -0.85
     Oren
    -0.84
     Yuri
    -0.84
    Ndr
    -0.83
    POSITIVE LOGITS
     Uniti
    0.92
    ので
    0.88
    InputBorder
    0.82
     Dutton
    0.72
    ICALS
    0.69
    a
    0.69
    epiece
    0.68
    ski
    0.67
    liger
    0.67
    bobox
    0.66
    Activations Density 2.333%

    No Known Activations