© 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. 20-GEMMASCOPE-RES-16K
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    arguments and evidence related to a specific claim or case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases containing strong argumentative language, particularly words related to making an argument or point.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.61
     Houſe
    -0.55
     betweenstory
    -0.54
     esternos
    -0.50
     tranſ
    -0.48
    ſelf
    -0.48
     Monfieur
    -0.47
    Autoritní
    -0.47
    ſelves
    -0.46
     Umgang
    -0.44
    POSITIVE LOGITS
     argument
    0.90
     justification
    0.88
     arguments
    0.88
     justifying
    0.81
     argue
    0.79
     proof
    0.78
     convincing
    0.78
     evidence
    0.76
     Argument
    0.75
     Justification
    0.75
    Activations Density 0.572%

    No Known Activations