© 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. 11-GEMMASCOPE-RES-16K
    11. 13721
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and relationships between variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActivatedRoute
    -0.58
    Referències
    -0.57
    jing
    -0.55
    hurst
    -0.55
    Cus
    -0.54
    utar
    -0.54
     Details
    -0.53
     Sagar
    -0.53
     details
    -0.53
     pitch
    -0.51
    POSITIVE LOGITS
     propOrder
    0.87
     AssemblyCulture
    0.84
    ंदीखरीदारी
    0.70
     than
    0.68
    مقاله
    0.66
     vuotta
    0.66
     inégal
    0.65
    OrEqualTo
    0.65
     >=",
    0.65
     <>",
    0.64
    Activations Density 0.680%

    No Known Activations