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. 20-GEMMASCOPE-RES-65K
    6. 1118
    Prev
    Next
    INDEX
    Explanations

    scientific and statistical terminology related to kinase activity and biological measurements

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

    comparisons of potency between different substances or compounds

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

    greater than, equals

    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
    ]--;
    -0.53
     (_,
    -0.50
    :')
    -0.49
    :");
    
    -0.48
    \#:
    -0.44
    สือ
    -0.44
    :}
    -0.44
     (_.
    -0.44
    ]+=
    -0.43
     berle
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.76
    AccessorTable
    0.75
     <
    0.62
    Спасылкі
    0.61
     ostavi
    0.61
     resourceCulture
    0.60
    dafx
    0.60
    ftagPool
    0.59
    +#+#
    0.58
     ==
    0.57
    Activations Density 1.301%

    No Known Activations