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. 4840
    Prev
    Next
    INDEX
    Explanations

    references to historical governance and conflicts in the context of the Abbasid Caliphate

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

    Following prepositions "of", "from", "to", "in"

    np_acts-logits-general · gemini-2.0-flash

    governor of Iraq, Merv, Balkh

    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
     itſelf
    -0.89
     myſelf
    -0.84
     Monfieur
    -0.82
     themſelves
    -0.79
     Mahomet
    -0.77
     Etrus
    -0.76
     Majefty
    -0.76
     Jefus
    -0.76
     Assyrian
    -0.73
     Huguen
    -0.73
    POSITIVE LOGITS
     modernes
    0.69
     lenker
    0.67
     decorativas
    0.66
     modernas
    0.62
     démocr
    0.59
     modernos
    0.58
    modern
    0.56
     sanitarias
    0.56
     domés
    0.55
     pájaros
    0.55
    Activations Density 0.272%

    No Known Activations