© 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. 15-GEMMASCOPE-RES-16K
    11. 1754
    Prev
    Next
    INDEX
    Explanations

    assertions or claims involving legal arguments or statements of fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.61
    EndContext
    -0.59
    PMailer
    -0.58
     queſta
    -0.57
    BagLayout
    -0.53
     GoogleFonts
    -0.52
    MergeFrom
    -0.49
     overheard
    -0.48
    Raycast
    -0.48
    :✨
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.52
    httphttps
    0.38
     defaultstate
    0.35
    说不
    0.35
     rằng
    0.32
    createTextNode
    0.32
     Lebens
    0.32
     Misalnya
    0.31
     whether
    0.30
     האם
    0.30
    Activations Density 1.193%

    No Known Activations