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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56592
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "set of" in various contexts

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

    set of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yavaş
    -0.52
     bahaya
    -0.41
     Swartz
    -0.40
     Geschwindigkeit
    -0.40
    TagMode
    -0.40
     sonriendo
    -0.40
     segreto
    -0.39
     reembolso
    -0.39
     encanta
    -0.39
     berlebihan
    -0.39
    POSITIVE LOGITS
     set
    0.80
    Set
    0.68
     Set
    0.66
     ſet
    0.62
     zestaw
    0.61
     sets
    0.61
    aset
    0.60
    set
    0.60
     seti
    0.59
     AttributeSet
    0.59
    Activations Density 0.027%

    No Known Activations