© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7381
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "According to" and variations involving references to other sources or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ogóle
    -0.73
    Външни
    -0.70
     alfo
    -0.66
    lectricité
    -0.66
     foglal
    -0.64
    ŚĆ
    -0.64
     kapcsolat
    -0.62
     igény
    -0.60
    łość
    -0.59
    ệc
    -0.58
    POSITIVE LOGITS
     Secondo
    1.21
    Según
    1.18
     Según
    1.16
     לפי
    1.15
    Selon
    1.15
    Secondo
    1.14
     Selon
    1.13
     according
    1.02
    according
    1.01
    Menurut
    1.00
    Activations Density 0.092%

    No Known Activations