© 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. 33-GEMMASCOPE-RES-16K
    11. 11936
    Prev
    Next
    INDEX
    Explanations

    phrases that mention advantages and benefits of specific techniques or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.45
    EndContext
    -0.43
    sique
    -0.41
    parseColor
    -0.41
     pessimistic
    -0.40
     Efq
    -0.38
    msgTypes
    -0.38
    Panamoan
    -0.38
     saddest
    -0.38
     Disagree
    -0.38
    POSITIVE LOGITS
     advantages
    2.69
     advantage
    2.33
     Advantages
    2.23
    advantages
    2.20
    Advantages
    2.17
     benefits
    2.13
     avantages
    2.05
     Vorteile
    2.05
     ventajas
    2.02
    advantage
    1.95
    Activations Density 0.687%

    No Known Activations