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. 10265
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of the word "the."

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

    "The" followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    the following noun

    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
     pinulongan
    -0.81
     RIPRODUZIONE
    -0.78
    الإنجليزية
    -0.71
     zelve
    -0.64
    FunctionFlags
    -0.64
    RectangleBorder
    -0.64
     lingue
    -0.62
    writeFieldEnd
    -0.60
     Shakspeare
    -0.60
    bootstrapcdn
    -0.60
    POSITIVE LOGITS
     new
    0.92
     
    0.83
     program
    0.80
     book
    0.79
     second
    0.79
     company
    0.76
     report
    0.76
     film
    0.75
     first
    0.75
     man
    0.74
    Activations Density 1.294%

    No Known Activations