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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12317
    Prev
    Next
    INDEX
    Explanations

    information related to oil and gas exploration and production activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lottesville
    -0.66
     الحره
    -0.52
     urbaine
    -0.51
     Fleisch
    -0.51
     gingival
    -0.50
     насељу
    -0.48
    cripciones
    -0.48
    rangea
    -0.47
     Symptom
    -0.47
     rabies
    -0.47
    POSITIVE LOGITS
     oil
    1.66
     Oil
    1.45
    oil
    1.42
    Oil
    1.39
     OIL
    1.36
    OIL
    1.17
     petroleum
    1.16
     Petroleum
    1.14
     crude
    1.04
    油
    1.03
    Activations Density 0.208%

    No Known Activations