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. 20-GEMMASCOPE-RES-16K
    6. 16235
    Prev
    Next
    INDEX
    Explanations

    activities related to outdoor recreation and sports

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

    Activities or hobbies

    np_acts-logits-general · gemini-2.0-flash

    people doing activities

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ContentAsync
    -0.85
    脚注の使い方
    -0.72
    WriteTagHelper
    -0.63
    Datuak
    -0.60
    ssysteme
    -0.59
     الحره
    -0.58
    RegressionTest
    -0.58
    RuleContext
    -0.57
    amerikanischer
    -0.57
    ainville
    -0.54
    POSITIVE LOGITS
     enthusiasts
    0.73
     enthusiast
    0.63
     expeditions
    0.62
     trips
    0.59
     excursions
    0.59
    KommentareTeilen
    0.57
     paradise
    0.56
     adventures
    0.54
     aficionados
    0.54
     excursion
    0.53
    Activations Density 0.170%

    No Known Activations