© 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. 36-GEMMASCOPE-RES-16K
    11. 8160
    Prev
    Next
    INDEX
    Explanations

    phrases related to verification and confirmation of facts or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.65
     EconPapers
    -0.59
     ſte
    -0.48
    󠁴
    -0.45
    ſelves
    -0.40
     otomatig
    -0.39
    ineſs
    -0.36
    vdots
    -0.36
     ſta
    -0.35
     leaſt
    -0.35
    POSITIVE LOGITS
     confirmation
    2.98
     confirm
    2.81
     confirmed
    2.80
     confirming
    2.67
     Confirm
    2.61
     confirms
    2.56
     Confirmation
    2.55
     confirmations
    2.55
    confirm
    2.48
     confirma
    2.42
    Activations Density 0.915%

    No Known Activations