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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7647
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sort."

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

    "sort" or "sort of"

    np_acts-logits-general · gemini-2.0-flash

    sort of

    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
    Extinguishing
    -0.56
    XmlAccessorType
    -0.54
     Roskov
    -0.52
    LLocation
    -0.52
    getDoctrine
    -0.51
    rstrip
    -0.50
    mampuan
    -0.48
    contentLoaded
    -0.48
    __);
    -0.47
    ngOnDestroy
    -0.47
    POSITIVE LOGITS
     SORT
    0.69
    ingly
    0.66
    RegressionTest
    0.61
     carat
    0.57
    Gord
    0.57
     Италијани
    0.56
    ation
    0.56
     Soll
    0.56
    WriteLiteral
    0.56
    fact
    0.54
    Activations Density 0.023%

    No Known Activations