© 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. 2-GEMMASCOPE-RES-16K
    11. 3624
    Prev
    Next
    INDEX
    Explanations

    terms related to destruction or killing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Courant
    -0.52
    ⎩
    -0.45
     Beaux
    -0.45
     inflex
    -0.45
     SCL
    -0.44
     Ramb
    -0.44
     conve
    -0.44
     exc
    -0.43
    Ramb
    -0.42
     Relig
    -0.42
    POSITIVE LOGITS
     destroy
    1.82
     destroys
    1.70
     destroying
    1.66
    destroy
    1.65
     destroyed
    1.62
     Destroy
    1.55
    Destroy
    1.51
     demolish
    1.48
     abolish
    1.45
     destruir
    1.45
    Activations Density 0.511%

    No Known Activations