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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4384
    Prev
    Next
    INDEX
    Explanations

    expressions related to self-interest versus the greater good

    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
    MockMvc
    -0.58
    abstractmethod
    -0.48
     ویکی‌پدیا
    -0.48
    شهاد
    -0.47
     Ause
    -0.47
    PDM
    -0.46
    cmath
    -0.46
    嘧
    -0.45
    rrggbb
    -0.45
    География
    -0.45
    POSITIVE LOGITS
     interests
    1.53
     Interests
    1.29
     benefit
    1.28
    interests
    1.26
     welfare
    1.21
    benefit
    1.12
     interest
    1.10
     intérêts
    1.07
     intereses
    1.05
     Benefit
    1.01
    Activations Density 0.279%

    No Known Activations