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. 13-GEMMASCOPE-RES-16K
    6. 14295
    Prev
    Next
    INDEX
    Explanations

    terms related to saliva or salivary functions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Koko
    -0.73
    <th>
    -0.69
     Dread
    -0.68
     ordonn
    -0.68
    Dread
    -0.65
     Withers
    -0.64
     popolari
    -0.62
    Koko
    -0.62
    Baylor
    -0.61
    <h2>
    -0.61
    POSITIVE LOGITS
     SAL
    1.28
    SAL
    1.20
     Salter
    1.15
    Sal
    1.11
     Sal
    1.09
    sal
    1.03
     salads
    1.03
     Salinity
    1.01
     salinity
    0.99
     salic
    0.98
    Activations Density 0.311%

    No Known Activations