© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5443
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax or structure related to functions and declarations

    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
    awtextra
    -0.76
    
    -0.70
    ChildScrollView
    -0.66
    matchCondition
    -0.65
     мәкал
    -0.65
    Personendaten
    -0.65
     الحره
    -0.65
     Wikimedijinoj
    -0.63
     चीज़ों
    -0.63
     ModelExpression
    -0.62
    POSITIVE LOGITS
    注明
    0.33
     kaldı
    0.32
     Hague
    0.32
     coû
    0.31
     Holi
    0.31
     başlay
    0.31
    persky
    0.30
     przed
    0.30
    Không
    0.29
    迎
    0.29
    Activations Density 0.776%

    No Known Activations