© 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. 35-GEMMASCOPE-RES-16K
    11. 7066
    Prev
    Next
    INDEX
    Explanations

    various code structure elements such as function definitions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.75
    EDEFAULT
    -0.68
    DoubleQuotes
    -0.63
    awtextra
    -0.60
    AndroidJUnit
    -0.59
    DebuggerStep
    -0.58
    DockStyle
    -0.57
    ftagPool
    -0.54
    EnableWeb
    -0.54
     snippetHide
    -0.53
    POSITIVE LOGITS
     Keuangan
    0.42
    loroethene
    0.37
     Membuat
    0.36
     Relaciones
    0.36
     imprimée
    0.35
    ご了承
    0.34
     tatuagens
    0.34
     tallas
    0.34
     selezione
    0.33
     Estable
    0.33
    Activations Density 0.126%

    No Known Activations