© 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. 7200
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and their properties in various contexts

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

    Mathematical/statistical variable or parameter

    np_acts-logits-general · gemini-2.0-flash

    mathematical quantifiers and symbols

    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
    +#+#
    -1.24
    #+#
    -0.97
    脚注の使い方
    -0.92
    NUMX
    -0.89
     الحره
    -0.86
    Personensuche
    -0.86
     незавершена
    -0.85
     estekak
    -0.81
     كومونز
    -0.81
    )•
    -0.79
    POSITIVE LOGITS
     $
    1.15
     $\
    0.94
     ${\
    0.78
     denoted
    0.72
     X
    0.70
     P
    0.63
     £
    0.61
     represented
    0.60
     <
    0.60
     A
    0.59
    Activations Density 2.962%

    No Known Activations