© 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. 37-GEMMASCOPE-RES-16K
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    elements related to criminal activity and legal proceedings

    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
    BufferException
    -0.45
    出版年
    -0.41
    parsedMessage
    -0.41
    \{\\
    -0.35
     createState
    -0.34
     endwhile
    -0.34
     économ
    -0.33
     createSprite
    -0.32
     conquista
    -0.32
     beleid
    -0.32
    POSITIVE LOGITS
     suspicious
    1.02
     suspects
    1.00
     clues
    0.96
     sospe
    0.94
     alibi
    0.94
     suspicion
    0.92
     suspicions
    0.91
     suspect
    0.89
     motive
    0.84
     implicated
    0.82
    Activations Density 1.107%

    No Known Activations