© 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. 35-GEMMASCOPE-RES-16K
    6. 8095
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with rates and measurements, particularly in financial or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.46
    ngdoc
    -0.45
     betweenstory
    -0.41
    刈
    -0.38
    Controllo
    -0.37
    Hozzáférés
    -0.35
     Alloc
    -0.35
    resz
    -0.35
     Asu
    -0.34
     arch
    -0.34
    POSITIVE LOGITS
     rate
    3.36
     rates
    3.06
     Rate
    2.98
    Rate
    2.86
    rate
    2.75
     Rates
    2.75
     RATE
    2.69
    Rates
    2.56
     RATES
    2.45
    rates
    2.44
    Activations Density 1.042%

    No Known Activations