© 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. 14170
    Prev
    Next
    INDEX
    Explanations

    references to searching the internet as a means to gather information or solve problems

    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
     دیکھیے
    -0.72
    PMailer
    -0.71
     kasarigan
    -0.68
    IsContent
    -0.66
    mergeFrom
    -0.66
    NUMX
    -0.63
     BorderRadius
    -0.63
    )++;
    -0.63
    AddTagHelper
    -0.60
    ">+
    -0.60
    POSITIVE LOGITS
     googling
    0.83
     googled
    0.81
     online
    0.71
     google
    0.67
     internet
    0.61
     Google
    0.60
     websites
    0.56
     web
    0.56
    調べ
    0.55
    google
    0.55
    Activations Density 0.192%

    No Known Activations