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. 14430
    Prev
    Next
    INDEX
    Explanations

    programming or coding syntax and structure

    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
    <bos>
    -0.60
    BeginContext
    -0.52
    ParallelGroup
    -0.49
     CreateTagHelper
    -0.48
     Poole
    -0.48
     Acetate
    -0.48
     SqlCommand
    -0.46
    enders
    -0.46
     acetate
    -0.45
     correcte
    -0.45
    POSITIVE LOGITS
    sleep
    1.34
     sleep
    1.10
    addCriterion
    1.03
    Sleep
    1.01
     Sleep
    0.96
    AsUp
    0.89
     WaitForSeconds
    0.88
     Wiktionnaire
    0.86
    InjectAttribute
    0.86
    expandindo
    0.85
    Activations Density 0.066%

    No Known Activations