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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24579
    Prev
    Next
    INDEX
    Explanations

    references to food and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ujednoznacz
    -0.59
     Савезне
    -0.51
    Билгалдахарш
    -0.50
     lenker
    -0.47
     disambiguazione
    -0.46
    Ironically
    -0.44
    verifyException
    -0.43
    ilitas
    -0.42
    Географиясе
    -0.41
    tronlink
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    0.44
    ariConfig
    0.44
    ApiOperation
    0.43
     setPassword
    0.43
     cuisines
    0.40
    OptionPane
    0.40
     ProgressDialog
    0.38
     plotted
    0.38
    corde
    0.38
    DataSetChanged
    0.37
    Activations Density 0.004%

    No Known Activations