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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6090
    Prev
    Next
    INDEX
    Explanations

    mentions of "interest" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoc
    -0.66
    WindowConstants
    -0.65
     NSCoder
    -0.64
    yntaxException
    -0.63
     Cabral
    -0.61
     Lokales
    -0.60
    HtmlAttribute
    -0.60
    opje
    -0.59
    GEBURTS
    -0.59
     gelukkig
    -0.58
    POSITIVE LOGITS
     interest
    5.38
     Interest
    4.85
    interest
    4.68
    Interest
    4.63
     INTEREST
    4.20
     interests
    3.84
    INTEREST
    3.64
     Interests
    3.47
     interés
    3.34
     interesse
    3.15
    Activations Density 0.091%

    No Known Activations