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. 11-GEMMASCOPE-RES-16K
    6. 6324
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fallu
    -0.55
     zijne
    -0.53
     homoto
    -0.50
     AppColors
    -0.49
    enschappelijke
    -0.46
    didReceive
    -0.46
     prismatic
    -0.45
     hindurch
    -0.45
    σθαι
    -0.45
    ῖς
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.78
     Biôgrafia
    0.72
    /**
    0.70
     Wicidata
    0.68
     kaarangay
    0.67
    afficheront
    0.63
    queryInterface
    0.63
    ArrowToggle
    0.62
    الحياه
    0.62
    InvalidProtocol
    0.61
    Activations Density 0.393%

    No Known Activations