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. 3-GEMMASCOPE-RES-16K
    6. 12344
    Prev
    Next
    INDEX
    Explanations

    phrases relating to taking advantage or exploiting opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iostream
    -0.54
    kär
    -0.50
    i
    -0.49
     cup
    -0.49
     Rät
    -0.48
     Holden
    -0.48
    awtextra
    -0.48
     numberOfRows
    -0.48
     insuffisamment
    -0.46
    Lester
    -0.45
    POSITIVE LOGITS
     benefiting
    1.48
     beneficiary
    1.44
     benefited
    1.43
     exploited
    1.41
     benefit
    1.41
     benefitted
    1.38
     aprovechar
    1.37
     exploit
    1.37
     aprovecha
    1.34
     Benef
    1.32
    Activations Density 0.112%

    No Known Activations