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. 4351
    Prev
    Next
    INDEX
    Explanations

    terms related to listings or classifications

    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
    ISupport
    -0.63
     kawa
    -0.61
    mailto
    -0.57
     שוליים
    -0.55
    addGroup
    -0.54
    Искәрмәләр
    -0.54
    Questions
    -0.53
    middag
    -0.52
     transforma
    -0.51
     Paradis
    -0.50
    POSITIVE LOGITS
     listed
    1.77
     listing
    1.70
     Listed
    1.56
     listings
    1.52
     Listing
    1.44
    Listed
    1.43
    listed
    1.42
    Listing
    1.25
     Listings
    1.25
     nakalista
    1.19
    Activations Density 0.250%

    No Known Activations