© 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. 22-GEMMASCOPE-RES-16K
    11. 14307
    Prev
    Next
    INDEX
    Explanations

    symbols and variable notations commonly used in mathematical equations and scientific contexts

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

    Mathematical or physics equations and symbols

    np_acts-logits-general · gemini-2.0-flash

    gamma, phi, j with > or }

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}}{
    -0.62
     }}-
    -0.58
    ırl
    -0.50
    ">'.$
    -0.48
     margarita
    -0.47
    IRQn
    -0.47
    }}{{
    -0.47
    ='.$
    -0.46
     }}{
    -0.46
    gain
    -0.45
    POSITIVE LOGITS
     $+\
    0.70
     $-\
    0.70
    出版年
    0.64
     تانيه
    0.64
    principalColumn
    0.64
     $=\
    0.63
    annica
    0.62
    >\
    0.61
     فريبيس
    0.60
    -\
    0.59
    Activations Density 2.373%

    No Known Activations