Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10246
    Prev
    Next
    INDEX
    Explanations

    specific navigation details, particularly directions and locations

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

    Numbers followed by street names

    np_acts-logits-general · gemini-2.0-flash

    street names or addresses

    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
     alright
    -0.79
     okay
    -0.78
     OKAY
    -0.65
     ok
    -0.64
    tagHelperRunner
    -0.61
     OK
    -0.61
     насељу
    -0.58
    hood
    -0.57
    okay
    -0.56
    KommentareTeilen
    -0.55
    POSITIVE LOGITS
     Main
    1.06
    Main
    0.91
     main
    0.76
     MAIN
    0.75
     Church
    0.73
    MAIN
    0.71
     Second
    0.64
     Market
    0.64
     Third
    0.62
    Church
    0.61
    Activations Density 0.112%

    No Known Activations