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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6221
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or organizations, particularly related to caspase and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mappedBy
    -0.67
    nesium
    -0.52
    edom
    -0.51
    mainPanel
    -0.49
    lexia
    -0.49
     civile
    -0.49
    styleable
    -0.49
    Amicalement
    -0.48
    {{{
    -0.48
    '){
    
    -0.48
    POSITIVE LOGITS
    Cas
    0.82
    cas
    0.81
     cas
    0.78
     Cas
    0.71
    omock
    0.70
    matchCondition
    0.69
    Geplaatst
    0.69
     airline
    0.68
     Airline
    0.67
    InsertCommand
    0.66
    Activations Density 0.060%

    No Known Activations