© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14604
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical stability and equilibrium in dynamic systems

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

    Tokens followed by "solution" or a similar word

    np_acts-logits-general · gemini-2.0-flash

    unique solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.51
    IBOutlet
    -0.50
    MockBean
    -0.50
    tagHelperRunner
    -0.48
    metics
    -0.48
     defaultstate
    -0.47
    BeginContext
    -0.47
    ついで
    -0.47
    ismet
    -0.46
     poveznice
    -0.45
    POSITIVE LOGITS
     solution
    1.20
     solutions
    1.20
     Solution
    1.01
     equilibrium
    0.99
    Solutions
    0.98
     Solutions
    0.98
     equilibria
    0.98
     soluciones
    0.96
    solution
    0.96
    solutions
    0.95
    Activations Density 2.094%

    No Known Activations