© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 5823
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to actions and events involving fire and political situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consenting
    -0.57
    ModelSerializer
    -0.56
     resorted
    -0.55
    новниш
    -0.55
     suffers
    -0.54
    fallen
    -0.54
     muere
    -0.52
    ########.
    -0.51
     lapses
    -0.51
     fallen
    -0.50
    POSITIVE LOGITS
     destroy
    1.01
     destroying
    0.97
     overthrow
    0.93
     oust
    0.90
     obliter
    0.89
     deth
    0.86
     destroys
    0.86
     beat
    0.84
     usur
    0.83
     disrupt
    0.83
    Activations Density 0.705%

    No Known Activations