© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6779
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying and troubleshooting problems

    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
    ifikationer
    -0.50
    BeginContext
    -0.48
     Италијани
    -0.48
     testimonio
    -0.47
     Italijanski
    -0.47
    Pant
    -0.47
    BufferException
    -0.47
    новниш
    -0.46
    IsPostBack
    -0.45
    ContextHolder
    -0.45
    POSITIVE LOGITS
     solve
    2.64
     solved
    2.54
     solves
    2.51
     solving
    2.46
     solution
    2.45
    solve
    2.23
     Solve
    2.17
    solution
    2.14
     Solving
    2.13
     Solution
    2.12
    Activations Density 0.940%

    No Known Activations