© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    elements related to web and document structure

    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
     Back
    -0.55
    Back
    -0.53
    back
    -0.52
     stri
    -0.45
     Bak
    -0.44
    Bak
    -0.44
    BACK
    -0.43
     macrop
    -0.43
     back
    -0.42
    bak
    -0.42
    POSITIVE LOGITS
     propOrder
    0.49
     autorytatywna
    0.45
    GenerationType
    0.43
     ویکی‌پدی
    0.42
     getItemId
    0.40
    PyTuple
    0.40
     Audiodateien
    0.39
    RTLI
    0.39
    cellence
    0.39
     romántico
    0.39
    Activations Density 1.280%

    No Known Activations