© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 9774
    Prev
    Next
    INDEX
    Explanations

    guidelines and evidence related to health and emergency risk communication

    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
     confiable
    -1.14
    ônicos
    -1.02
     flavorful
    -0.95
     computadora
    -0.95
    ighborhood
    -0.93
    Neighbors
    -0.92
     neighborhoods
    -0.91
     econômica
    -0.91
     aluminum
    -0.90
     uș
    -0.90
    POSITIVE LOGITS
    Whilst
    1.80
     Whilst
    1.70
    initialise
    1.61
     enquiries
    1.58
     specialises
    1.56
     Enquiries
    1.55
     realised
    1.51
     tyres
    1.51
     recognisable
    1.50
    Colour
    1.50
    Activations Density 5.565%

    No Known Activations