© 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. 15191
    Prev
    Next
    INDEX
    Explanations

    statements indicating agreement or consistency in findings across studies

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

    "in" followed by words indicating agreement/alignment

    np_acts-logits-general · gemini-2.0-flash

    in agreement with or in line with

    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
     useRouter
    -0.56
    Nguồn
    -0.50
    ClientSize
    -0.49
    retudo
    -0.48
    assertNotNull
    -0.48
     occupe
    -0.47
    sbericht
    -0.47
    
    -0.46
     '*':
    -0.45
    unehmen
    -0.43
    POSITIVE LOGITS
     consistent
    1.33
    consistent
    1.28
    Consistent
    1.28
     Consistent
    1.23
     contrary
    1.23
    contr
    1.05
     contradicts
    1.05
     aligns
    1.04
     conforms
    1.02
     contradict
    1.02
    Activations Density 0.781%

    No Known Activations