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. 6998
    Prev
    Next
    INDEX
    Explanations

    terms related to bicycles and their components

    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
     myſelf
    -0.80
     typelib
    -0.78
     saites
    -0.78
     Monfieur
    -0.73
    Personendaten
    -0.70
     itſelf
    -0.69
     Efq
    -0.68
    ViewFeatures
    -0.67
    AnimationsModule
    -0.67
    anneer
    -0.66
    POSITIVE LOGITS
     bicycle
    0.70
     bike
    0.68
     bici
    0.65
    bike
    0.64
     Bike
    0.60
    ExecuteReader
    0.60
     bicic
    0.56
    Bike
    0.54
     Bicycle
    0.54
    PYX
    0.53
    Activations Density 2.556%

    No Known Activations