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. 15-GEMMASCOPE-RES-16K
    6. 2381
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lease
    -0.48
     Welsh
    -0.47
    小说
    -0.45
    Welsh
    -0.45
     québéco
    -0.45
     colina
    -0.45
     내
    -0.45
    domésticos
    -0.45
     maș
    -0.43
     ongles
    -0.43
    POSITIVE LOGITS
     global
    1.38
     worldwide
    1.32
     globally
    1.19
    global
    1.17
     weltweit
    1.14
     countries
    1.12
     international
    1.11
     mondial
    1.08
    worldwide
    1.06
    lobal
    1.06
    Activations Density 0.611%

    No Known Activations