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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6654
    Prev
    Next
    INDEX
    Explanations

    references to the concept of comedy, comedians, and related handlers in the context of coding or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yy
    -0.66
     Online
    -0.59
     
    -0.57
    <unused63>
    -0.57
    <unused61>
    -0.56
     .
    -0.56
     U
    -0.55
    .
    -0.54
     Z
    -0.54
    ​
    -0.54
    POSITIVE LOGITS
     myſelf
    1.39
     Efq
    1.38
     itſelf
    1.34
     Majefty
    1.29
     Monfieur
    1.25
    存于互联网档案馆
    1.24
     becauſe
    1.22
     leaſt
    1.18
     Forumite
    1.13
     Theſe
    1.12
    Activations Density 0.233%

    No Known Activations