© 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. 36-GEMMASCOPE-RES-16K
    11. 8074
    Prev
    Next
    INDEX
    Explanations

    patterns of formatting or structure, such as slashes and underscores in text or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.82
    ementara
    -0.80
     $_(
    -0.80
     ſind
    -0.79
    desertcart
    -0.78
     surla
    -0.78
     témoig
    -0.77
     kasarigan
    -0.77
    pantalones
    -0.75
    WebElementEntity
    -0.75
    POSITIVE LOGITS
     Feinde
    0.31
    Redacción
    0.29
     olmayan
    0.28
    retudo
    0.28
     године
    0.28
    CppCodeGen
    0.28
    ฯ
    0.27
    Véase
    0.27
    όμε
    0.27
     fehlen
    0.27
    Activations Density 0.485%

    No Known Activations