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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 5877
    Prev
    Next
    INDEX
    Explanations

    elements related to figures and equations in scientific text

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

    Mathematical or statistical notations

    np_acts-logits-general · gemini-2.0-flash

    synonymous non-synonymous coding regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dropIfExists
    -0.39
     idéia
    -0.33
     tags
    -0.33
     Bewußt
    -0.31
     \"
    -0.30
     \#
    -0.30
     RIPRODUZIONE
    -0.29
    didSet
    -0.29
     Gegenteil
    -0.29
    Véxase
    -0.29
    POSITIVE LOGITS
    httphttps
    0.62
    <sup>
    0.56
     AssemblyCompany
    0.53
     '\\;'
    0.52
    Fandom
    0.51
     muualla
    0.51
    клопе
    0.50
    setVerticalGroup
    0.50
    xygen
    0.49
     GBIF
    0.48
    Activations Density 3.274%

    No Known Activations