© 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. 41-GEMMASCOPE-RES-16K
    11. 10575
    Prev
    Next
    INDEX
    Explanations

    keywords and declarations related to programming constructs such as static variables and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.87
     himself
    -0.87
     themselves
    -0.86
     yourself
    -0.85
    itself
    -0.80
     herself
    -0.77
    themselves
    -0.76
     Himself
    -0.75
     Yourself
    -0.73
    himself
    -0.72
    POSITIVE LOGITS
    ally
    0.64
    ALLY
    0.59
     readonly
    0.50
     constexpr
    0.47
    ically
    0.46
     utafitiHapana
    0.44
    mente
    0.44
    setVerticalGroup
    0.42
    intenant
    0.41
    tically
    0.40
    Activations Density 0.135%

    No Known Activations