© 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. 7304
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts and database design

    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
     ujednoznacz
    -0.49
     TAMBÉM
    -0.32
    乓
    -0.32
     LUMP
    -0.31
    MLLoader
    -0.31
     TAMBIÉN
    -0.30
     OHIO
    -0.28
    TestingModule
    -0.28
     Keaton
    -0.28
     Royal
    -0.28
    POSITIVE LOGITS
     SR
    1.70
     LR
    1.56
     MR
    1.55
     XR
    1.55
    SR
    1.53
     NR
    1.50
     VR
    1.46
     WR
    1.45
     ZR
    1.45
     JR
    1.43
    Activations Density 1.978%

    No Known Activations