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. 40261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "created" and related variations

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

    creation date or time

    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
    rungsseite
    -0.72
     disambiguazione
    -0.71
    principalColumn
    -0.64
     betrekking
    -0.56
     ujednoznacz
    -0.56
     eventName
    -0.56
     IBOutlet
    -0.53
    ValueStyle
    -0.52
     snippetHide
    -0.52
    routeProvider
    -0.52
    POSITIVE LOGITS
     Created
    0.54
    Created
    0.51
     created
    0.51
     creation
    0.50
    Creation
    0.48
     onCreate
    0.47
    CreatedDate
    0.47
     Creation
    0.44
    CreatedAt
    0.44
    created
    0.44
    Activations Density 0.010%

    No Known Activations