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. 1435
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving parentheses and exponents

    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
    Vidu
    -0.54
    вид
    -0.53
     vulgaris
    -0.48
    nál
    -0.48
     stewards
    -0.48
     pensato
    -0.47
     encima
    -0.46
    voja
    -0.46
     brug
    -0.46
    deld
    -0.46
    POSITIVE LOGITS
    )^{
    1.29
    )^
    1.23
    })^{
    1.04
    })^
    0.98
    ))^
    0.95
    )^{-
    0.93
    клопе
    0.93
    )^{\
    0.91
    )^(
    0.90
    AddTagHelper
    0.89
    Activations Density 0.596%

    No Known Activations