© 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. 23-GEMMASCOPE-RES-16K
    11. 8547
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer software and installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.70
    ########.
    -0.60
    tanleria
    -0.56
    rungsseite
    -0.55
    withIdentifier
    -0.54
     ویکی‌پدیا
    -0.54
    KindOfClass
    -0.51
     Réponses
    -0.51
    CppCodeGen
    -0.50
    KeySpec
    -0.49
    POSITIVE LOGITS
    ۜ
    0.39
     yağ
    0.36
     markets
    0.35
     muualla
    0.35
    appendTo
    0.33
     host
    0.32
     chez
    0.31
     city
    0.31
     سطح
    0.30
     opérés
    0.30
    Activations Density 1.132%

    No Known Activations