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. 3-GEMMASCOPE-RES-16K
    6. 6441
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     front
    -0.60
     ролях
    -0.54
    idelberg
    -0.54
    ubov
    -0.51
    Front
    -0.51
     horno
    -0.50
     "
    -0.50
     po
    -0.50
     Front
    -0.50
    خبار
    -0.50
    POSITIVE LOGITS
    private
    1.31
     private
    0.94
     Private
    0.85
    PreferredItem
    0.85
     PRIVATE
    0.84
     privado
    0.81
    Private
    0.81
     privados
    0.78
     FetchType
    0.78
    PRIVATE
    0.78
    Activations Density 0.078%

    No Known Activations