© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11640
    Prev
    Next
    INDEX
    Explanations

    references to religious institutions and discussions surrounding faith and church attendance

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

    after "visit" or variations of "visit"

    np_acts-logits-general · gemini-2.0-flash

    visits to places

    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
    脚注の使い方
    -0.67
    
    -0.63
     sleepers
    -0.60
    UIControlState
    -0.60
    \{\\
    -0.59
    TagMode
    -0.58
    
    -0.58
    PyExc
    -0.57
    anthene
    -0.57
     ostavi
    -0.56
    POSITIVE LOGITS
     visit
    2.21
     visits
    2.07
     visited
    2.00
    visit
    1.96
     visiting
    1.92
    Visit
    1.77
     Visit
    1.71
     Visits
    1.68
    visits
    1.66
     VISIT
    1.64
    Activations Density 0.302%

    No Known Activations