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. 4-GEMMASCOPE-RES-16K
    6. 783
    Prev
    Next
    INDEX
    Explanations

    mentions of oil and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.60
     Locomo
    -0.55
     Вікіпе
    -0.55
     Cuth
    -0.54
     bles
    -0.53
    ByExample
    -0.53
     besti
    -0.52
     mand
    -0.52
    antMatchers
    -0.52
    Bres
    -0.51
    POSITIVE LOGITS
     oil
    2.98
     Oil
    2.84
    Oil
    2.69
     OIL
    2.68
    oil
    2.65
     oils
    2.48
    OIL
    2.43
     Oils
    2.37
     olie
    1.89
     Öl
    1.85
    Activations Density 0.037%

    No Known Activations