© 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. 36-GEMMASCOPE-RES-16K
    11. 7724
    Prev
    Next
    INDEX
    Explanations

    references to legal and political frameworks surrounding citizenship and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proactively
    -0.88
     showcasing
    -0.87
     leveraging
    -0.85
     moniker
    -0.85
     incentiv
    -0.82
     prioritizing
    -0.82
     showcased
    -0.81
     blurry
    -0.78
     seamlessly
    -0.78
     prioriti
    -0.78
    POSITIVE LOGITS
     skall
    0.46
     muß
    0.43
     employés
    0.40
     vrou
    0.39
     fotográfica
    0.38
     rôles
    0.38
     belang
    0.37
     läßt
    0.36
    faßt
    0.36
     bleue
    0.36
    Activations Density 2.092%

    No Known Activations