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. 3979
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to topology and set theory

    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
     متعلقه
    -0.65
    onViewCreated
    -0.61
    enumii
    -0.60
    drawSprites
    -0.57
    abestanden
    -0.56
    دانشنامهٔ
    -0.56
    LabelTagHelper
    -0.53
     <>",
    -0.53
     decou
    -0.51
     balans
    -0.51
    POSITIVE LOGITS
    ⊆
    0.96
     subset
    0.95
    subset
    0.93
    subseteq
    0.89
     subsets
    0.88
    subsets
    0.83
    seteq
    0.76
    ⊂
    0.73
     DbSet
    0.69
    HashSet
    0.69
    Activations Density 1.006%

    No Known Activations