© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2597
    Prev
    Next
    INDEX
    Explanations

    specific symbols or formatting elements used in text documents, particularly those indicating structure or references

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

    mathematical notation and document structural symbols like brackets and parentheses.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     שוליים
    -0.55
    ----</
    -0.55
    MessageOf
    -0.50
    wpi
    -0.47
    exitRule
    -0.47
    Portály
    -0.47
     Canti
    -0.47
     Antif
    -0.45
     Fragments
    -0.45
    новниш
    -0.44
    POSITIVE LOGITS
    multirow
    0.63
    }{*}{
    0.51
    dafx
    0.49
     absorción
    0.48
     Voraussetzung
    0.47
     Bewegungen
    0.46
     Planung
    0.46
     pertemuan
    0.45
     Gründung
    0.45
     selben
    0.45
    Activations Density 0.006%

    No Known Activations