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. 11-GEMMASCOPE-RES-16K
    6. 5792
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "final" and references to object instances in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.81
    FailureListener
    -0.75
     XCTest
    -0.62
     thiết
    -0.59
    stdc
    -0.57
     propOrder
    -0.56
    Zunanje
    -0.54
    ResumeLayout
    -0.54
     RoutedEventArgs
    -0.54
     PyObject
    -0.54
    POSITIVE LOGITS
    yntaxException
    0.73
     myſelf
    0.65
    Спасылкі
    0.63
    parsedMessage
    0.62
    windowFixed
    0.62
    äsident
    0.61
     لينك
    0.61
    COUVER
    0.61
    abestanden
    0.61
     Comprar
    0.60
    Activations Density 0.020%

    No Known Activations