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. 45656
    Prev
    Next
    INDEX
    Explanations

    references to applications, specifically in the context of programming and frameworks

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

    "my" prefix followed by a specific noun

    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
    coroutines
    -0.50
    SqlCommand
    -0.48
    rdquo
    -0.48
    {~
    -0.46
     boll
    -0.46
     Boll
    -0.43
    setcounter
    -0.43
    ulemon
    -0.42
    FetchType
    -0.42
    ceptre
    -0.42
    POSITIVE LOGITS
     MyApp
    1.88
    MyApp
    1.53
    myapp
    0.96
    myModal
    0.76
     Meksiku
    0.74
     للاسماء
    0.72
    uxxxx
    0.70
    mycompany
    0.68
     mijne
    0.67
     AssemblyCulture
    0.66
    Activations Density 0.001%

    No Known Activations