Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14036
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fulfillment, compliance, and adherence to rules or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trav
    -0.50
    ärä
    -0.48
     investment
    -0.47
    lague
    -0.47
     createSprite
    -0.46
    BeginContext
    -0.45
    CRD
    -0.45
    جع
    -0.44
     aho
    -0.44
    ldb
    -0.44
    POSITIVE LOGITS
     fulfill
    1.03
     fulfil
    1.00
     cumplir
    0.96
     fulfills
    0.94
    fulfilled
    0.87
     fulf
    0.85
    Suivez
    0.85
    mybatisplus
    0.84
     fulfilling
    0.84
     fulfilled
    0.83
    Activations Density 0.327%

    No Known Activations