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

    Neuronpedia

    Jacobian LensNEW
    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. 559
    Prev
    Next
    INDEX
    Explanations

    terms related to theft and criminal activities

    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
     rapporti
    -0.40
     aanges
    -0.38
     Relationship
    -0.38
     relationship
    -0.37
    awakeFromNib
    -0.37
    Dış
    -0.36
     Arrange
    -0.35
    Risultati
    -0.35
    pNext
    -0.34
    Verweise
    -0.34
    POSITIVE LOGITS
     theft
    1.15
     steal
    1.12
     thefts
    1.09
     stolen
    1.09
     steals
    1.07
     stealing
    1.04
     robbery
    1.02
    Theft
    1.02
    stolen
    1.02
     Theft
    1.02
    Activations Density 0.312%

    No Known Activations