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. 12769
    Prev
    Next
    INDEX
    Explanations

    references to scripting and programming code, particularly JavaScript

    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
    حياته
    -0.94
     NEA
    -0.86
     Efq
    -0.84
    endphp
    -0.81
    posedge
    -0.80
    солю
    -0.79
     poffible
    -0.78
    belline
    -0.76
     {:.
    -0.74
     />";
    -0.73
    POSITIVE LOGITS
     script
    2.66
     scripts
    2.50
     Script
    2.43
    script
    2.22
     Scripts
    2.21
    Script
    2.21
     SCRIPT
    2.12
    SCRIPT
    1.98
    scripts
    1.85
    Scripts
    1.84
    Activations Density 0.075%

    No Known Activations