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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2660
    Prev
    Next
    INDEX
    Explanations

    phrases related to long-term duration or processes

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

    "Long"

    np_acts-logits-general · gemini-2.0-flash

    long duration or extent

    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
    tonode
    -0.91
    Datuak
    -0.84
     Monfieur
    -0.80
     bezeichneter
    -0.75
     myſelf
    -0.74
    })));
    -0.74
    queryInterface
    -0.72
    $.
    
    -0.71
    ();)
    -0.70
     AssemblyTitle
    -0.70
    POSITIVE LOGITS
     LONG
    0.95
     long
    0.94
     Long
    0.90
    long
    0.89
    Long
    0.86
     ago
    0.86
     term
    0.82
     Longo
    0.78
    LONG
    0.77
     lasting
    0.73
    Activations Density 0.160%

    No Known Activations