© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8958
    Prev
    Next
    INDEX
    Explanations

    assertions and opinions regarding ethical considerations about warfare and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leveraging
    -0.85
     insights
    -0.79
     learnings
    -0.74
     impactful
    -0.69
     timelines
    -0.68
     통해
    -0.68
     robust
    -0.67
    pectives
    -0.66
     prioriti
    -0.66
     prioritized
    -0.65
    POSITIVE LOGITS
     sortes
    0.75
     somebody
    0.73
     supuestamente
    0.71
     vestiti
    0.71
     people
    0.69
     quelqu
    0.66
     stupid
    0.66
    OpenHelper
    0.65
     coû
    0.65
     pubblicità
    0.64
    Activations Density 2.906%

    No Known Activations