© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9416
    Prev
    Next
    INDEX
    Explanations

    terms related to low values, specifically in contexts of ranking or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    ParallelGroup
    -0.54
    tagHelper
    -0.53
    HttpEntity
    -0.51
     entityManager
    -0.45
     JAXBElement
    -0.45
    CDCl
    -0.44
    OrBuilder
    -0.43
    routeProvider
    -0.43
    inquirer
    -0.43
    OGND
    -0.43
    POSITIVE LOGITS
     low
    3.66
     Low
    3.30
    Low
    3.22
     LOW
    3.00
    low
    2.95
    低
    2.66
    LOW
    2.59
     低
    2.33
     низ
    2.23
     düşük
    2.20
    Activations Density 0.089%

    No Known Activations