© 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. 3-GEMMASCOPE-RES-16K
    11. 593
    Prev
    Next
    INDEX
    Explanations

    iterations or repetitions in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Och
    -0.54
    xxi
    -0.52
    chapper
    -0.48
     IActionResult
    -0.47
    DropColumn
    -0.47
     Discre
    -0.47
    Detach
    -0.47
    pragma
    -0.46
     mobi
    -0.45
     فت
    -0.45
    POSITIVE LOGITS
     repeating
    1.56
     repetition
    1.55
     repeats
    1.52
     répé
    1.48
     repeat
    1.45
     Repetition
    1.45
     Repe
    1.41
     repetir
    1.38
     repeated
    1.38
    Repeating
    1.36
    Activations Density 0.296%

    No Known Activations