Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1561
    Prev
    Next
    INDEX
    Explanations

    phrases related to numbers and statistics

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

    after "and"

    np_acts-logits-general · gemini-2.0-flash

    listing conjunctions and abstract nouns

    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
     épaules
    -1.26
     vœux
    -1.16
     âmes
    -1.12
     lèvres
    -1.11
     pouvoirs
    -1.09
     dieux
    -1.06
     bienfaits
    -1.03
     genoux
    -1.01
     négociations
    -0.97
     attentes
    -0.96
    POSITIVE LOGITS
     ones
    0.92
     الحره
    0.74
     histories
    0.69
     structures
    0.67
     scenarios
    0.67
     situations
    0.65
     philosophies
    0.65
     statuses
    0.65
     layouts
    0.65
     systems
    0.65
    Activations Density 0.782%

    No Known Activations