Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6090
    Prev
    Next
    INDEX
    Explanations

    words and variations related to the term "Bel"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.12
    NUMX
    -0.98
    tagHelperRunner
    -0.98
    ViewFeatures
    -0.95
     Numerade
    -0.95
    migrationBuilder
    -0.93
    PyExc
    -0.93
    ^(@)
    -0.92
    parsedMessage
    -0.89
    )");
    
    -0.89
    POSITIVE LOGITS
     Bel
    3.26
    Bel
    2.98
     bel
    2.89
    bel
    2.70
     BEL
    2.52
    BEL
    2.37
     Бел
    1.53
     BELL
    1.37
     Belk
    1.27
     Belinda
    1.27
    Activations Density 0.081%

    No Known Activations