© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4681
    Prev
    Next
    INDEX
    Explanations

    references to political movements and organizational terms

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

    Abbreviations and acronyms followed by parenthesis

    np_acts-logits-general · gemini-2.0-flash

    acronyms ending in D

    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
    FetchType
    -0.46
     Ashraf
    -0.42
     Hauser
    -0.42
     Brunner
    -0.41
    Portale
    -0.39
     Василь
    -0.38
     Alfaro
    -0.38
    AnchorStyles
    -0.38
     Cowper
    -0.37
     Ruskin
    -0.36
    POSITIVE LOGITS
     PD
    1.10
     Kud
    1.10
     SD
    1.09
     RD
    1.08
     LD
    1.08
     CSD
    1.08
     FD
    1.07
     VD
    1.05
    PD
    1.04
     GD
    1.04
    Activations Density 1.854%

    No Known Activations