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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8993
    Prev
    Next
    INDEX
    Explanations

    events related to violent incidents or deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    violent crime and death events, particularly murders, shootings, and violent attacks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nantinya
    -0.51
     artık
    -0.45
     nanti
    -0.44
     actualidad
    -0.44
     Verfügung
    -0.43
    intenant
    -0.42
    hichever
    -0.41
     decât
    -0.40
     dahulu
    -0.40
     samenwerking
    -0.39
    POSITIVE LOGITS
     reportedly
    0.79
     allegedly
    0.73
     suspected
    0.68
     apparently
    0.68
     fatally
    0.65
     unattended
    0.64
     attempting
    0.62
    apparently
    0.62
     diduga
    0.62
     injuring
    0.62
    Activations Density 0.390%

    No Known Activations