© 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. 9549
    Prev
    Next
    INDEX
    Explanations

    references to accountability and collective responsibility

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

    language related to organizational leadership, employee feedback, and workplace culture management.

    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
     muß
    -0.87
     idéia
    -0.87
    faßt
    -0.81
     daß
    -0.78
     läßt
    -0.77
     Daß
    -0.75
    🖒
    -0.69
     mußten
    -0.67
     europé
    -0.66
     mußte
    -0.64
    POSITIVE LOGITS
     impactful
    0.92
     foundational
    0.85
     transformative
    0.77
     aligns
    0.75
     
    0.73
     LGBTQ
    0.73
     curated
    0.73
     decarbon
    0.71
    . 
    0.71
     nuanced
    0.70
    Activations Density 0.867%

    No Known Activations