© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7976
    Prev
    Next
    INDEX
    Explanations

    details related to electric guitars and their components

    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
    
    -0.46
    SharedCtor
    -0.39
     uParam
    -0.37
     DKI
    -0.36
    entiary
    -0.35
    Disney
    -0.34
    testdata
    -0.34
     Rukh
    -0.34
     dataSet
    -0.33
    Biden
    -0.33
    POSITIVE LOGITS
     strings
    1.13
     tuning
    0.98
     string
    0.96
     Strings
    0.95
     intonation
    0.92
    Tuning
    0.90
     fret
    0.89
     frets
    0.88
     Tuning
    0.87
    strings
    0.86
    Activations Density 0.117%

    No Known Activations