© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16229
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical functions and iterative methods in numerical analysis

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

    Iterative algorithms and convergence

    np_acts-logits-general · gemini-2.0-flash

    iterative methods and convergence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.54
     Parlement
    -0.47
     AppCompatTheme
    -0.47
    kheim
    -0.47
     الحره
    -0.46
     Zay
    -0.46
    mick
    -0.45
     widowed
    -0.44
     legislator
    -0.44
     StatelessWidget
    -0.44
    POSITIVE LOGITS
     convergence
    1.00
     iterations
    0.89
     iteration
    0.89
     iterate
    0.83
     iterative
    0.82
     converges
    0.80
     iter
    0.80
     Convergence
    0.79
    Convergence
    0.79
     converged
    0.79
    Activations Density 0.912%

    No Known Activations