© 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. 5-GEMMASCOPE-RES-16K
    11. 13972
    Prev
    Next
    INDEX
    Explanations

    elements related to iterative processes and their convergence behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     khoa
    -0.59
     card
    -0.59
    jure
    -0.58
     fact
    -0.58
     Schult
    -0.55
    Rudolf
    -0.52
     Bunting
    -0.52
    etted
    -0.51
    hadiran
    -0.51
    ═
    -0.50
    POSITIVE LOGITS
     []:
    1.67
    hasNext
    1.55
     convergence
    1.27
     Convergence
    1.15
    convergence
    1.14
    Convergence
    1.14
     converges
    1.13
    ContentAsync
    1.13
    mstyle
    1.07
     converge
    1.06
    Activations Density 0.020%

    No Known Activations