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. 12-GEMMASCOPE-RES-16K
    6. 12170
    Prev
    Next
    INDEX
    Explanations

    specific business and economic terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.78
     الوطنيه
    -0.66
     ennemis
    -0.65
     indisponible
    -0.64
     publicitaires
    -0.64
    feitura
    -0.64
     doble
    -0.63
    ruecos
    -0.62
     engraçadas
    -0.62
     mecán
    -0.61
    POSITIVE LOGITS
     sector
    0.80
     sectors
    0.72
     industry
    0.69
     industries
    0.66
    sector
    0.59
     products
    0.59
     */;
    0.58
     industrial
    0.52
    Portail
    0.51
     services
    0.51
    Activations Density 0.306%

    No Known Activations