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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13057
    Prev
    Next
    INDEX
    Explanations

    references to oil and gas resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ByExample
    -0.91
    culata
    -0.81
     tramonto
    -0.78
     menti
    -0.78
    addPreferredGap
    -0.78
    Precalculus
    -0.77
    BibitemShut
    -0.76
     presencial
    -0.76
     Γ
    -0.75
     Már
    -0.75
    POSITIVE LOGITS
     oil
    1.61
     OIL
    1.57
     Oil
    1.54
     oils
    1.51
     Oils
    1.42
    oil
    1.42
    OIL
    1.38
    Oil
    1.38
    油
    1.14
     olie
    1.09
    Activations Density 0.048%

    No Known Activations