© 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. 33-GEMMASCOPE-RES-16K
    11. 908
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases that imply deceit or false representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    serviceWorker
    -0.47
    MigrationBuilder
    -0.47
     kaynağından
    -0.47
    CompleteListener
    -0.46
    execSQL
    -0.45
     Wiktionnaire
    -0.45
    argout
    -0.45
    SharedDtor
    -0.44
    حوالہ
    -0.43
     GenerationType
    -0.43
    POSITIVE LOGITS
     fake
    2.58
    fake
    2.20
     Fake
    2.17
     pretended
    2.14
     faked
    2.13
     faking
    2.09
    Fake
    2.09
     pretend
    2.08
     pretending
    2.02
     phony
    2.00
    Activations Density 1.255%

    No Known Activations