© 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. 21-GEMMASCOPE-RES-16K
    11. 2150
    Prev
    Next
    INDEX
    Explanations

    terms related to business and investment activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     qualunque
    -0.53
    VersionUID
    -0.52
     whatever
    -0.49
     cavalli
    -0.47
     actuels
    -0.46
     varsa
    -0.45
     qualsiasi
    -0.45
     sebagainya
    -0.44
     commerciaux
    -0.44
     africains
    -0.43
    POSITIVE LOGITS
     firm
    1.25
     giant
    1.20
     company
    1.08
     insurer
    1.03
     automaker
    1.02
     manufacturer
    0.99
     provider
    0.97
     developer
    0.97
     retailer
    0.96
     watchdog
    0.94
    Activations Density 0.368%

    No Known Activations