© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 426
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation 'SD' and related terms denoting statistical variance or standard deviation in measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sup
    -0.48
     lu
    -0.47
     Vir
    -0.47
    ParallelGroup
    -0.46
     world
    -0.46
     dul
    -0.46
     lou
    -0.46
    dou
    -0.45
     span
    -0.45
     word
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.90
     valamint
    0.82
     sowie
    0.81
     oraz
    0.81
    sowie
    0.78
    новниш
    0.75
     sekä
    0.75
    oredCriteria
    0.74
     nonché
    0.73
     ainsi
    0.73
    Activations Density 0.263%

    No Known Activations