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. 823
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or amounts

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

    terms related to financial performance and rankings

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

    carrying, taking, bringing

    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
    bala
    -0.53
    PrototypeOf
    -0.51
    ilizar
    -0.50
    BeginContext
    -0.50
    oa̍t
    -0.49
    atigable
    -0.48
     вое
    -0.48
    risation
    -0.48
    ambique
    -0.47
     Himo
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.66
     kasarigan
    0.60
    олові
    0.56
    تفصیلات
    0.53
     pinulongan
    0.53
    клопе
    0.53
     circon
    0.47
     '\\;'
    0.47
    nein
    0.47
    +#+#
    0.46
    Activations Density 0.107%

    No Known Activations