© 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. 22-GEMMASCOPE-RES-16K
    11. 9294
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to stability and fluctuations in dynamic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Stable/unstable states, solutions, regimes, or equilibria

    np_acts-logits-general · gemini-2.0-flash

    stable solutions and attractors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.49
    dí
    -0.45
    født
    -0.44
    libft
    -0.43
    otides
    -0.43
     randint
    -0.42
     Gehirn
    -0.42
     HttpServlet
    -0.40
    rrggbb
    -0.40
     kasarigan
    -0.39
    POSITIVE LOGITS
     solutions
    1.17
     solution
    1.16
     stable
    1.03
     Solution
    1.01
    Solutions
    1.00
    solution
    0.98
     stability
    0.97
     soluciones
    0.97
    Solution
    0.97
    solutions
    0.96
    Activations Density 2.040%

    No Known Activations