© 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. 37-GEMMASCOPE-RES-16K
    11. 4670
    Prev
    Next
    INDEX
    Explanations

    financial disclaimers and cautions regarding liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftance
    -0.45
     demoral
    -0.40
     Fortunately
    -0.40
     Interestingly
    -0.40
    Increment
    -0.39
     basics
    -0.39
    Decrement
    -0.38
     trick
    -0.38
     Initially
    -0.38
    getNum
    -0.38
    POSITIVE LOGITS
    httphttps
    0.75
     hereby
    0.71
    DISCLAIMER
    0.69
     ProtoMessage
    0.69
     herein
    0.69
     AssemblyCulture
    0.67
     typelib
    0.66
    LookAnd
    0.65
     Haftung
    0.65
     neither
    0.64
    Activations Density 0.878%

    No Known Activations