© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4014
    Prev
    Next
    INDEX
    Explanations

    references to deception or falsehoods in the context of news or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.64
     فريبيس
    -0.58
    Cyfarwyddwr
    -0.56
    Jîn
    -0.53
     समीक्षक
    -0.51
     Infórmanos
    -0.50
     useCallback
    -0.47
    surate
    -0.47
    rawDesc
    -0.47
    ViewFeatures
    -0.46
    POSITIVE LOGITS
     fake
    1.99
     false
    1.75
     Fake
    1.68
     faked
    1.66
    fake
    1.66
    Fake
    1.63
     deception
    1.63
     faking
    1.58
     fakes
    1.58
     phony
    1.55
    Activations Density 1.375%

    No Known Activations