© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 13009
    Prev
    Next
    INDEX
    Explanations

    phrases related to mechanical maintenance or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.54
    faker
    -0.52
    ulantes
    -0.52
    AutoresizingMask
    -0.52
    centerY
    -0.52
     تانيه
    -0.51
    جستارهای
    -0.49
     AssemblyCompany
    -0.48
    כח
    -0.48
    SequentialGroup
    -0.48
    POSITIVE LOGITS
     buildup
    1.24
     build
    1.21
     clogging
    1.15
     accumulation
    1.12
     stuck
    1.10
     clog
    1.09
     blockage
    1.09
     clogs
    1.08
     clogged
    1.08
     blocked
    1.07
    Activations Density 0.324%

    No Known Activations