© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2628
    Prev
    Next
    INDEX
    Explanations

    references to ongoing legal issues and disputes

    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
     vroeger
    -0.61
     Loved
    -0.59
     Later
    -0.59
    当時は
    -0.58
     later
    -0.58
     toen
    -0.56
     Subsequently
    -0.56
     später
    -0.55
     was
    -0.55
     Afterward
    -0.55
    POSITIVE LOGITS
     currently
    1.39
    currently
    1.30
     presently
    1.21
     actuellement
    1.20
     derzeit
    1.17
     now
    1.15
    Currently
    1.10
     Currently
    1.09
     obecnie
    1.02
     attualmente
    1.00
    Activations Density 0.477%

    No Known Activations