© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10966
    Prev
    Next
    INDEX
    Explanations

    references to gas and related terminology

    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
     AssemblyTitle
    -1.24
    ]='\
    -0.91
     fidèles
    -0.85
    loài
    -0.84
     Loja
    -0.82
    ]]]
    -0.82
     uncin
    -0.81
     Numerology
    -0.81
    venido
    -0.80
    ]][
    -0.80
    POSITIVE LOGITS
     gas
    1.69
     GAS
    1.58
     Gas
    1.52
    gas
    1.51
    GAS
    1.49
    Gas
    1.48
     gases
    1.00
     Gaspar
    0.98
     Gass
    0.97
    ガス
    0.95
    Activations Density 0.052%

    No Known Activations