© 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. 24-GEMMASCOPE-RES-16K
    11. 4834
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "J" in various contexts

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

    Text following the letter "J"

    np_acts-logits-general · gemini-2.0-flash

    J followed by names or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserModule
    -0.61
     sord
    -0.49
     LCCN
    -0.47
    mapTo
    -0.46
    Espèce
    -0.45
    addCriterion
    -0.45
    amante
    -0.45
     Outlook
    -0.44
    HasKey
    -0.43
     conso
    -0.43
    POSITIVE LOGITS
    MLLoader
    0.72
    AndEndTag
    0.70
     Normdatei
    0.67
    StoryboardSegue
    0.66
     للاسماء
    0.62
     transfieras
    0.60
     Lightboxes
    0.57
    RegistryLite
    0.56
    цездатний
    0.56
    HasAnnotation
    0.56
    Activations Density 0.188%

    No Known Activations