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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28515
    Prev
    Next
    INDEX
    Explanations

    punctuation and contextual structures within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Clik
    -0.67
    imageio
    -0.57
    NewGuid
    -0.50
    Diweddarwch
    -0.50
     OnTriggerEnter
    -0.48
    لينكات
    -0.48
     occa
    -0.48
    كويكب
    -0.47
     चीज़ों
    -0.46
    ạy
    -0.45
    POSITIVE LOGITS
     Already
    1.32
     already
    1.32
    Already
    1.24
    already
    1.20
     currently
    1.12
     이미
    1.02
    すでに
    1.01
    既に
    1.00
     ALREADY
    1.00
     Currently
    0.99
    Activations Density 0.140%

    No Known Activations