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. 3424
    Prev
    Next
    INDEX
    Explanations

    references to individual entities or items in a list or collection

    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
    ulon
    -0.55
    PSE
    -0.52
    StackNavigator
    -0.52
    хла
    -0.51
     useContext
    -0.51
    <![
    -0.51
    rinol
    -0.51
    //
    -0.50
    нулся
    -0.50
    ardan
    -0.50
    POSITIVE LOGITS
     each
    4.46
    each
    3.80
    Each
    3.77
     Each
    3.73
     EACH
    3.40
     chaque
    3.34
    EACH
    3.32
    Chaque
    3.05
     every
    2.98
     Chaque
    2.88
    Activations Density 0.082%

    No Known Activations