© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3546
    Prev
    Next
    INDEX
    Explanations

    references to processes involving communication or arrangement

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

    Preposition "by" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    by followed by a noun or gerund

    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
    VersionUID
    -0.66
     AssemblyProduct
    -0.59
     recev
    -0.57
    lamy
    -0.56
    AddHtmlAttribute
    -0.56
    OOTDTY
    -0.53
     rispond
    -0.51
     tantôt
    -0.51
     automatiques
    -0.51
     répar
    -0.51
    POSITIVE LOGITS
     email
    0.67
     referendum
    0.65
     مشين
    0.64
     mail
    0.61
    MEMORANDUM
    0.60
     proclamation
    0.57
    Portail
    0.56
     decree
    0.55
     stealth
    0.54
    Eloquent
    0.54
    Activations Density 0.304%

    No Known Activations