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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7222
    Prev
    Next
    INDEX
    Explanations

    references to names or brands, particularly variations of the name "Brion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "bri", "dri", "gri", or "ri"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ri, bri, gri, dri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DNEY
    -0.51
     cliquez
    -0.50
    %)$
    -0.50
    rood
    -0.48
    maßen
    -0.48
     MutableLiveData
    -0.48
    EnableWeb
    -0.46
     lunak
    -0.46
     bolig
    -0.46
    opensource
    -0.46
    POSITIVE LOGITS
    RoutingModule
    0.60
     Italijani
    0.57
     SEDS
    0.56
    queryInterface
    0.56
    oredCriteria
    0.55
    cri
    0.54
    awaiter
    0.54
    principalTable
    0.53
    ">//
    0.52
     cri
    0.50
    Activations Density 0.175%

    No Known Activations