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. 20-GEMMASCOPE-RES-16K
    6. 14057
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     errorCode
    -0.53
     незавершена
    -0.51
    RetentionPolicy
    -0.51
    Substitute
    -0.50
    exitRule
    -0.49
    err
    -0.48
     ADVIS
    -0.48
    else
    -0.47
     refusé
    -0.47
     défin
    -0.46
    POSITIVE LOGITS
     виправивши
    0.80
    GEBURTSDATUM
    0.75
    OGND
    0.74
    EndProject
    0.68
     kasarigan
    0.68
    المناصب
    0.66
     >=",
    0.66
     ***!
    0.65
     AssemblyTitle
    0.65
    andowski
    0.61
    Activations Density 0.041%

    No Known Activations