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. 211
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations and names of institutions

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

    references to school administration and budgetary concerns

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

    florida locations

    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
     CreateTagHelper
    -0.62
    MockMvc
    -0.61
     springfox
    -0.60
     fieldNum
    -0.59
    idum
    -0.58
    tirol
    -0.58
    رشف
    -0.57
    })));
    -0.55
    Referensi
    -0.55
     Wiktionnaire
    -0.54
    POSITIVE LOGITS
     Tampa
    0.82
    Tampa
    0.74
     Hillsborough
    0.67
     Tamp
    0.66
    tampa
    0.65
     Pin
    0.65
     pewter
    0.60
     Clearwater
    0.59
     USF
    0.57
    Pin
    0.57
    Activations Density 0.116%

    No Known Activations