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. 7316
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "contact us" or reaching out for assistance

    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
     pó
    -0.78
     DataType
    -0.72
     Karak
    -0.71
     Olimpia
    -0.71
     Confe
    -0.70
     Charlemagne
    -0.68
    izable
    -0.68
     Chy
    -0.68
     CCP
    -0.68
     symbo
    -0.67
    POSITIVE LOGITS
     us
    2.22
     Us
    1.68
    Us
    1.45
     ourselves
    1.25
     We
    1.20
     our
    1.15
     нас
    1.13
     нам
    1.10
    us
    1.10
     we
    1.09
    Activations Density 0.048%

    No Known Activations