© 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. 21-GEMMASCOPE-RES-16K
    11. 13249
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their identifiers in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.60
     reír
    -0.56
     CURIAM
    -0.53
     kentang
    -0.53
     noDo
    -0.53
     sarili
    -0.52
     calcetines
    -0.52
     الحره
    -0.52
    hésite
    -0.51
     dată
    -0.51
    POSITIVE LOGITS
    Dina
    0.46
    حياته
    0.44
    حياتها
    0.44
    Aziz
    0.40
    دانشنامهٔ
    0.40
    geslacht
    0.38
     Rabat
    0.38
    Referências
    0.37
    haustible
    0.37
     оригіналу
    0.37
    Activations Density 0.065%

    No Known Activations