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. 2959
    Prev
    Next
    INDEX
    Explanations

    elements related to spirituality and religious worship

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

    Follows prepositions or numbers

    np_acts-logits-general · gemini-2.0-flash

    evil, signifies, intensity, 8, deficiency

    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
    -0.69
    ibrill
    -0.59
    
    -0.56
    TagHelper
    -0.54
     AssemblyCulture
    -0.54
    expandindo
    -0.54
     Nazareth
    -0.53
    سطس
    -0.52
     Allein
    -0.51
     Glas
    -0.51
    POSITIVE LOGITS
    CPtr
    0.58
     arany
    0.52
     '\\;'
    0.51
     vyu
    0.50
     putra
    0.50
    transQ
    0.50
     samband
    0.50
     pintados
    0.50
     henvisninger
    0.48
    Kanada
    0.48
    Activations Density 0.120%

    No Known Activations