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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8641
    Prev
    Next
    INDEX
    Explanations

    references to headquarters, upgrades, and musical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abstrait
    -0.48
     leyendas
    -0.47
     abstrato
    -0.46
     campeones
    -0.45
     serpiente
    -0.45
     inmediata
    -0.45
     Vereine
    -0.44
     Gegend
    -0.44
     ediciones
    -0.43
     liitty
    -0.43
    POSITIVE LOGITS
    Autowired
    0.82
     Inclusive
    0.73
    Inclusion
    0.71
     headquarters
    0.69
    inclusion
    0.69
     Inclusion
    0.68
     Knock
    0.65
     Headquarters
    0.65
     necessity
    0.63
     immune
    0.63
    Activations Density 0.081%

    No Known Activations