© 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. 34-GEMMASCOPE-RES-16K
    11. 10154
    Prev
    Next
    INDEX
    Explanations

    references to legal punishment, particularly capital punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.43
     Spuren
    -0.38
    ✭✭
    -0.35
    hibli
    -0.35
    Przypisy
    -0.35
     emergencia
    -0.34
    yordu
    -0.33
    
    -0.33
    Embeddable
    -0.32
     pfle
    -0.32
    POSITIVE LOGITS
     execution
    1.66
     executions
    1.48
     Execution
    1.43
     executed
    1.34
    execution
    1.34
     EXEC
    1.30
    Execution
    1.28
     executes
    1.25
     execute
    1.23
     executing
    1.20
    Activations Density 0.514%

    No Known Activations