© 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. 11-GEMMASCOPE-RES-16K
    11. 5680
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 't' and expressions defining functions or types in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esfuer
    -0.54
    használ
    -0.48
     ferons
    -0.47
     Kapol
    -0.45
    ckså
    -0.44
     izvē
    -0.44
     enfans
    -0.43
     csalá
    -0.42
     posesión
    -0.42
     Kebijakan
    -0.42
    POSITIVE LOGITS
    t
    1.46
     t
    0.85
    т
    0.74
    ｔ
    0.68
    tC
    0.67
    ت
    0.64
    tance
    0.64
    期刊论文
    0.63
    T
    0.61
    TargetException
    0.59
    Activations Density 0.124%

    No Known Activations