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. 8621
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "Bu" entities or names

    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
    ValueStyle
    -0.78
    InjectAttribute
    -0.67
    NameInMap
    -0.64
     &___
    -0.63
     Cora
    -0.63
     BART
    -0.63
     TestBed
    -0.61
    ränkt
    -0.61
    SequentialGroup
    -0.60
    XmlEnum
    -0.60
    POSITIVE LOGITS
     Bu
    3.26
     bu
    3.19
    Bu
    3.06
    bu
    2.75
     BU
    2.25
    BU
    2.05
     Buchanan
    1.75
     Buc
    1.61
     Buk
    1.60
     Бу
    1.55
    Activations Density 0.090%

    No Known Activations