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. 15371
    Prev
    Next
    INDEX
    Explanations

    keywords related to formal responsibilities and tasks

    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
    cdnjs
    -0.58
    ска
    -0.49
     financially
    -0.48
    ặt
    -0.48
    rxjs
    -0.47
    bihan
    -0.47
     legale
    -0.45
     safest
    -0.44
     сму
    -0.44
     temporarily
    -0.43
    POSITIVE LOGITS
     integrating
    0.87
     integration
    0.85
     integrate
    0.83
    Gambas
    0.82
     integrated
    0.79
    Integrating
    0.79
     integrates
    0.78
    EndGlobalSection
    0.76
     collaborative
    0.75
     participatory
    0.75
    Activations Density 0.243%

    No Known Activations