© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    references to the Bluemix platform and Docker technology

    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
     متعلقه
    -0.96
    Portail
    -0.86
    RenderAtEndOf
    -0.80
     Portail
    -0.78
    ########.
    -0.77
     Paula
    -0.76
    存于互联网档案馆
    -0.72
    ribadian
    -0.71
    createServer
    -0.70
    TestingModule
    -0.70
    POSITIVE LOGITS
    DMETHOD
    0.78
    صار
    0.75
    ISSION
    0.72
     Aung
    0.71
     GOS
    0.71
     Lyons
    0.70
    ĸ
    0.69
    SLP
    0.69
     DAS
    0.68
     IMS
    0.66
    Activations Density 0.902%

    No Known Activations