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. 1-GEMMASCOPE-RES-16K
    6. 9503
    Prev
    Next
    INDEX
    Explanations

    terms related to exclusivity or elite status

    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
    SpringBootTest
    -0.63
    urbation
    -0.58
    IActionResult
    -0.58
     MaterialApp
    -0.57
    mbols
    -0.56
    APIView
    -0.56
    ✨:
    -0.55
    ButtonModule
    -0.54
     dejes
    -0.54
    Ђ
    -0.54
    POSITIVE LOGITS
     exclu
    1.36
     exclusive
    1.34
     elite
    1.33
    Exclusive
    1.23
     Exclusive
    1.21
     exclude
    1.20
    exclusive
    1.18
    elite
    1.17
     exclusivity
    1.15
     excluded
    1.11
    Activations Density 0.066%

    No Known Activations