© 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. 20-GEMMASCOPE-RES-16K
    6. 4744
    Prev
    Next
    INDEX
    Explanations

    complicated relationships and interactions between concepts and entities

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

    legal and negotiation language, particularly words related to disputes and settlements.

    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
    VYMaps
    -0.56
    principalColumn
    -0.52
     Pest
    -0.50
    Pest
    -0.48
    CloseOperation
    -0.46
     Obrador
    -0.44
    pest
    -0.44
    CodedInputStream
    -0.44
    istoitu
    -0.43
    Sucesor
    -0.43
    POSITIVE LOGITS
    お互
    0.85
    各自
    0.79
     respective
    0.74
     masing
    0.73
     both
    0.72
     saling
    0.72
     mutually
    0.68
    それぞれ
    0.68
    どちらも
    0.67
     ambos
    0.66
    Activations Density 0.475%

    No Known Activations