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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 433
    Prev
    Next
    INDEX
    Explanations

    references to incidents or events related to significant occurrences

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

    references to incidents, particularly in a healthcare or regulatory context

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

    incident reporting, precipitation, light, particle, cardiovascular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{
    -0.62
    MetaType
    -0.60
    CURLOPT
    -0.54
    PU
    -0.53
     Tavares
    -0.53
    fillType
    -0.53
    wack
    -0.53
    weetened
    -0.52
    цездатний
    -0.52
    ništvo
    -0.52
    POSITIVE LOGITS
     متعلقه
    1.03
     Incidents
    0.92
    ality
    0.91
    ally
    0.89
     incidents
    0.87
    uality
    0.87
    alities
    0.74
     itſelf
    0.71
    Occurred
    0.71
    als
    0.69
    Activations Density 0.024%

    No Known Activations