© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues and regulations

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

    followed by prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    verbs and verb forms

    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
     "..\..\..\
    -1.00
    tvguidetime
    -0.92
     "..\..\
    -0.88
     للاسماء
    -0.80
    DataAnnotations
    -0.76
     оригіналу
    -0.76
    iformis
    -0.75
    bootstrapcdn
    -0.75
    Демографія
    -0.74
     المعيارى
    -0.74
    POSITIVE LOGITS
    ings
    0.95
    ing
    0.94
    ingly
    0.80
    able
    0.71
    inge
    0.69
    fully
    0.69
    ded
    0.67
    in
    0.62
    ments
    0.60
    d
    0.57
    Activations Density 0.594%

    No Known Activations