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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1763
    Prev
    Next
    INDEX
    Explanations

    commands related to managing data or tasks in a structured system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.59
    annon
    -0.54
     juridiques
    -0.50
    oltán
    -0.50
     financières
    -0.49
     RestTemplate
    -0.49
     milled
    -0.48
     culturelles
    -0.47
    apimachinery
    -0.47
     popolare
    -0.47
    POSITIVE LOGITS
    Datuak
    0.75
     متعلقه
    0.73
     للاسماء
    0.73
    #+#
    0.66
     estekak
    0.62
     الرياضيه
    0.61
    labus
    0.56
    Geografía
    0.56
    :+:
    0.53
     <=",
    0.53
    Activations Density 0.050%

    No Known Activations