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. 12897
    Prev
    Next
    INDEX
    Explanations

    concepts related to socio-cultural analysis and individualized experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     McIn
    -0.55
     Collabor
    -0.55
    dopodob
    -0.54
     Teamwork
    -0.53
     encourag
    -0.53
     nicknamed
    -0.52
     Administr
    -0.52
     astute
    -0.52
     bullish
    -0.51
    RegressionTest
    -0.51
    POSITIVE LOGITS
    onViewCreated
    0.68
    حياته
    0.65
    basicConfig
    0.65
     createState
    0.64
     EconPapers
    0.64
     onBind
    0.60
    eficent
    0.59
    WriteTagHelper
    0.57
    BoxShadow
    0.57
     onto
    0.57
    Activations Density 0.395%

    No Known Activations