© 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. 15-GEMMASCOPE-RES-16K
    11. 2812
    Prev
    Next
    INDEX
    Explanations

    references to scams and fraudulent online behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     served
    -0.28
     clock
    -0.27
     appréci
    -0.26
    WritableDatabase
    -0.26
     public
    -0.25
     directed
    -0.24
     shaped
    -0.24
     slou
    -0.24
     serves
    -0.24
     aisles
    -0.23
    POSITIVE LOGITS
    UserScript
    0.93
     SwitchCompat
    0.84
    MigrationBuilder
    0.83
    RegistryLite
    0.80
    Hentet
    0.78
    ⤹
    0.78
     scammers
    0.77
     scams
    0.77
     scam
    0.77
    ImageContext
    0.75
    Activations Density 0.347%

    No Known Activations