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. 5-GEMMASCOPE-RES-16K
    6. 13320
    Prev
    Next
    INDEX
    Explanations

    references to dryness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.90
    BeginContext
    -0.89
    */].
    -0.87
    StoryboardSegue
    -0.83
    المراجع
    -0.81
    مصادر
    -0.77
    LabelTagHelper
    -0.76
     Balloons
    -0.75
     Soccerway
    -0.74
     Hadid
    -0.73
    POSITIVE LOGITS
     dry
    2.23
     Dry
    2.15
     DRY
    2.11
    Dry
    2.08
    dry
    1.96
     dries
    1.77
    DRY
    1.74
     dried
    1.56
     drying
    1.51
     trock
    1.42
    Activations Density 0.048%

    No Known Activations