© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5447
    Prev
    Next
    INDEX
    Explanations

    references to political ideologies and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incentiv
    -0.84
    ​​​​​​​
    -0.69
     tasked
    -0.69
     LGBTQ
    -0.68
     millennials
    -0.67
    https
    -0.66
     prioritize
    -0.64
     impactful
    -0.64
     prioritise
    -0.63
     جدًا
    -0.63
    POSITIVE LOGITS
     mußten
    0.89
     muß
    0.87
     läßt
    0.85
     Daß
    0.85
     daß
    0.84
    faßt
    0.84
     mußte
    0.82
     Schluß
    0.76
     employes
    0.75
     idéia
    0.75
    Activations Density 1.120%

    No Known Activations