© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1587
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and negotiations

    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
    újo
    -0.55
    ConstraintMaker
    -0.54
    "%
    -0.54
     berdua
    -0.54
     resourceCulture
    -0.53
    }>{
    -0.52
    choly
    -0.52
    kinci
    -0.51
    essoal
    -0.50
    aternion
    -0.49
    POSITIVE LOGITS
     them
    3.63
     they
    2.77
    them
    2.73
     They
    2.66
    They
    2.54
    它们
    2.39
    they
    2.33
    它們
    2.18
     mereka
    2.17
     них
    2.17
    Activations Density 1.982%

    No Known Activations