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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53095
    Prev
    Next
    INDEX
    Explanations

    terms related to tobacco usage and health-related interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    health and substance use care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aluminium
    -0.83
     aluminium
    -0.79
    Aluminium
    -0.77
    httphttps
    -0.69
    Colours
    -0.68
     specialises
    -0.67
     tumours
    -0.66
     specialising
    -0.66
     realisation
    -0.66
    aluminium
    -0.66
    POSITIVE LOGITS
     @"/
    0.69
     statewide
    0.60
     blumen
    0.58
     resiliency
    0.57
     community
    0.55
     outreach
    0.54
     trainings
    0.54
     bike
    0.54
     transitioning
    0.54
    Serves
    0.53
    Activations Density 0.147%

    No Known Activations