© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11343
    Prev
    Next
    INDEX
    Explanations

    elements related to theoretical modeling and experimental validation in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀔
    -0.43
     bea
    -0.43
     dem
    -0.42
    webElementXpaths
    -0.41
    ROL
    -0.41
    
    -0.40
    夏
    -0.39
     bera
    -0.39
    MED
    -0.39
    rop
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.69
    FunctionFlags
    0.55
     ModelExpression
    0.54
     modeling
    0.51
    modeling
    0.50
    Modeling
    0.48
     modelling
    0.48
    Portale
    0.47
    ſelf
    0.47
     Modeling
    0.46
    Activations Density 1.562%

    No Known Activations