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. 2026
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging or diagnostic procedures related to the chest

    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
    #{
    -0.47
    ("")]
    
    -0.45
     ويكيميديا
    -0.45
     alcance
    -0.45
    DispatchToProps
    -0.45
    tamen
    -0.45
    躇
    -0.44
    /#{
    -0.43
    manship
    -0.43
    ayanan
    -0.43
    POSITIVE LOGITS
     photographs
    0.95
     photos
    0.95
     photograph
    0.91
     photo
    0.86
     foto
    0.83
     selfies
    0.82
     pictures
    0.77
     images
    0.76
    photo
    0.76
     fotos
    0.75
    Activations Density 0.268%

    No Known Activations